Benchmark Almanac

LMArena (Elo)

Gemini 4 Carbon 1,526 leads since October 2026
Gemini 4 Carbon 1,526 leads since October 2026
Fading

People chat with two anonymous models side by side and vote for the better reply. Votes become Elo-style ratings for each model.

The 2025 paper The Leaderboard Illusion reported that some labs tested many private variants before release. Arena changes vote filters and the rating fit over time, for example two bias terms added on May 12th, 2026, so old and new ratings drift. Arena Expert, added November 5th, 2025, ranks the hardest 5.5% of prompts.

Released
May 2023
Kind
Overall chat quality
Scored
Ranked by votes
Answers
Open-ended
Strongest model tested
Gemini 4 Carbon #2 on the capability index
Last in a launch post
March 2026, dropped before it saturated
Last model added
November 2026
Scores refreshed
November 12th, 2026

In the authors’ words

Large Language Models (LLMs) have unlocked new capabilities and applications; however, evaluating the alignment with human preferences still poses significant challenges. To address this issue, we introduce Chatbot Arena, an open platform for evaluating LLMs based on human preferences. Our methodology employs a pairwise comparison approach and leverages input from a diverse user base through crowdsourcing. The platform has been operational for several months, amassing over 240K votes. This paper describes the platform, analyzes the data we have collected so far, and explains the tried-and-true statistical methods we are using for efficient and accurate evaluation and ranking of models. We confirm that the crowdsourced questions are sufficiently diverse and discriminating and that the crowdsourced human votes are in good agreement with those of expert raters. These analyses collectively establish a robust foundation for the credibility of Chatbot Arena. Because of its unique value and openness, Chatbot Arena has emerged as one of the most referenced LLM leaderboards, widely cited by leading LLM developers and companies. Our demo is publicly available at https://chat.lmsys.org.

Abstract of Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference (arXiv:2403.04132, CC0)
385
Entries on its own leaderboard, 335 models we track
6
Launch posts list it, from 4 labs
13
System cards report it, from 5 labs

Gemini 4 Carbon leads with 1,526

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

Gemini 4 Carbon leads with 1,526, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

385 entries. Scroll sideways for the rest. Bars start at 800.

  1. 1,526 Gemini 4 Carbon
  2. 1,522 Gemini 4 Argon
  3. 1,511 Muse Wonder
  4. 1,506 Claude Opus 5.5
  5. 1,504 Claude Fable 5
  6. 1,503 Claude Opus 4.6
  7. 1,503 Claude Fable 5.1
  8. 1,501 Claude Opus 4.7
  9. 1,497 Gemini 3.8 Flash
  10. 1,496 Muse Spark 1.3
  11. 1,493 Muse Spark 1.2
  12. 1,491 Muse Spark 1.1
  13. 1,490 Claude Opus 5
  14. 1,489 Gemini 3.7 Flash
  15. 1,489 Muse Spark
  16. 1,487 Kimi K3
  17. 1,487 Gemini 3.1 Pro
  18. 1,486 Gemini 3 Pro
  19. 1,485 GPT-5.6 Sol
  20. 1,484 Qwen 3.8 Max
  21. 1,483 Kimi K3.1 Pro
  22. 1,483 Gemini 3.6 Flash
  23. 1,483 GLM-5.3
  24. 1,482 GPT-6.1 Sol
  25. 1,482 Claude Opus 4.8
  26. 1,481 GPT-5.5
  27. 1,480 MiMo-V2.6 Pro
  28. 1,478 Gemini 3.5 Flash
  29. 1,476 GPT-5.2 Instant
  30. 1,475 GPT-5.4
  31. 1,475 GLM-5.2
  32. 1,475 DeepSeek V4.1 Flash
  33. 1,475 Grok 4.20 Beta 1
  34. 1,474 GLM-5.3-Flash
  35. 1,474 GPT-6 Astra
  36. 1,474 Qwen3.7-Max
  37. 1,474 Claude Opus 4.5
  38. 1,473 GPT-5.5 Instant
  39. 1,473 Gemini 3 Flash
  40. 1,472 Claude Sonnet 5.5
  41. 1,472 Grok 4.20 Beta (Reasoning, 0309)
  42. 1,472 Claude Sonnet 4.6
  43. 1,471 Grok 4.20 Multi-Agent Beta (0309)
  44. 1,468 GPT-5.6 Terra
  45. 1,467 ERNIE 5.1
  46. 1,467 MiMo-V2.5-Pro
  47. 1,466 Grok 4.5
  48. 1,465 Grok 4.1
  49. 1,465 GLM-5.1
  50. 1,465 Qwen3.5-Max-Preview
  51. 1,464 DeepSeek-V4-Pro
  52. 1,461 Claude Sonnet 5
  53. 1,461 Kimi K2.6
  54. 1,460 Qwen 3.6 Max (Preview)
  55. 1,457 GLM-5
  56. 1,457 GPT-6 Sol
  57. 1,457 Seed2.0 Pro
  58. 1,456 Grok 4.6
  59. 1,456 Claude Sonnet 4.5
  60. 1,455 GPT-5.1
  61. 1,455 Qwen3.7-Plus
  62. 1,455 Gemini 3.5 Flash-Lite
  63. 1,454 Tencent Hy3
  64. 1,453 GPT-5.6 Luna
  65. 1,452 Gemma 4 31B IT
  66. 1,450 GPT-5.3 Instant
  67. 1,450 Claude Opus 4.1
  68. 1,450 Kimi K2.5
  69. 1,449 ERNIE-5.0-Preview (1203)
  70. 1,448 Step 5 Preview
  71. 1,448 MiMo-V2-Pro
  72. 1,448 MiMo-V2.6 Flash
  73. 1,447 GPT-5.4 Mini
  74. 1,446 ERNIE 5.0 (0110)
  75. 1,446 Gemini 2.5 Pro
  76. 1,445 GPT-4.5
  77. 1,443 Inkling
  78. 1,443 Qwen 3.6 Plus
  79. 1,443 GPT-4o
  80. 1,442 Grok 4.7
  81. 1,442 Grok 4.3
  82. 1,441 Qwen3.5 397B-A17B
  83. 1,441 GLM-4.7
  84. 1,441 GPT-6 Luna
  85. 1,439 DeepSeek-V4-Flash
  86. 1,437 Gemma 4 26B A4B
  87. 1,437 GPT-5.2
  88. 1,436 LongCat-Flash-Chat Exp (2602)
  89. 1,436 MiniMax-M3
  90. 1,435 GPT-5
  91. 1,435 Beam 1.0
  92. 1,434 Qwen3-Max
  93. 1,434 GLM-5V-Turbo
  94. 1,434 MiMo-V2.5
  95. 1,433 Qwen 3.8 27B
  96. 1,433 Gemini 3.1 Flash-Lite
  97. 1,432 o3
  98. 1,431 Grok 4.1 Fast
  99. 1,430 MiMo-V2-Omni
  100. 1,430 Kimi K2 Thinking Turbo
  101. 1,427 GPT-5 Chat
  102. 1,427 amazon-nova-experimental-chat (26-02-10)
  103. 1,427 Mistral Medium 3.5
  104. 1,426 Nemotron 3 Ultra
  105. 1,426 Claude Opus 4
  106. 1,425 DeepSeek-V3.2-Exp
  107. 1,425 DeepSeek-V3.2
  108. 1,425 Muse Glimmer
  109. 1,424 GLM-4.6
  110. 1,423 Mistral Large 4
  111. 1,422 Claude Haiku 5.5
  112. 1,422 Qwen3-235B-A22B-Instruct
  113. 1,421 DeepSeek-R1
  114. 1,418 Grok 4 Fast
  115. 1,418 Kimi K2
  116. 1,418 ERNIE-5.0-Preview (1022)
  117. 1,418 Kimi K2
  118. 1,417 DeepSeek-V3.1
  119. 1,416 Qwen3.5-122B-A10B
  120. 1,416 DeepSeek-V3.1-Terminus
  121. 1,415 Nemotron 3.5 Super VL
  122. 1,415 MiniMax-M2.7
  123. 1,415 Mistral Large 3
  124. 1,415 GPT-4.1
  125. 1,414 Claude Haiku 4.5
  126. 1,413 Qwen3-VL-235B-A22B-Instruct
  127. 1,412 Inkling 2 Small
  128. 1,412 amazon-nova-experimental-chat (26-01-10)
  129. 1,411 Grok 3
  130. 1,411 GLM-4.5
  131. 1,411 Grok 4
  132. 1,409 Gemini 2.5 Flash
  133. 1,409 Tencent Hy3 preview
  134. 1,409 Qwen3.5-27B
  135. 1,408 Mistral Medium 3.1
  136. 1,405 Inkling-Small
  137. 1,403 Gemini 2.5 Flash
  138. 1,402 o1
  139. 1,402 Qwen3-235B-A22B
  140. 1,402 Claude Sonnet 4
  141. 1,401 GPT-5.4 Nano
  142. 1,400 LongCat-Flash-Chat
  143. 1,400 Qwen3-235B-A22B-Thinking
  144. 1,399 Qwen3-Next-80B-A3B-Instruct
  145. 1,398 DeepSeek-R1
  146. 1,396 Qwen3.5-Flash
  147. 1,395 DeepSeek-V3
  148. 1,395 Qwen3-VL-235B-A22B
  149. 1,394 Hunyuan Vision 1.5 Thinking
  150. 1,394 Qwen3.5-35B-A3B
  151. 1,393 Step 3.5 Flash
  152. 1,393 amazon-nova-experimental-chat (12-10)
  153. 1,392 MiMo-V2-Flash
  154. 1,391 o4-mini
  155. 1,391 MiniMax-M2.5
  156. 1,390 GPT-5 mini
  157. 1,389 o1-preview
  158. 1,388 Claude 3.7 Sonnet
  159. 1,388 Qwen3-Coder-480B-A35B
  160. 1,387 Solar Pro 4
  161. 1,387 Hunyuan-T1
  162. 1,387 Mistral Medium 3
  163. 1,384 MiniMax-M2.1
  164. 1,383 Hunyuan-TurboS
  165. 1,383 GPT-4.1 mini
  166. 1,382 Qwen3-30B-A3B-Instruct
  167. 1,379 Gemini 2.5 Flash-Lite
  168. 1,379 Trinity Large Preview
  169. 1,378 GLM-4.6V
  170. 1,375 Gemini 2.5 Flash-Lite
  171. 1,374 Claude 3.5 Sonnet (October 2024)
  172. 1,374 Qwen2.5-Max
  173. 1,373 GLM-4.5-Air
  174. 1,369 Qwen3-Next-80B-A3B
  175. 1,367 Trinity Large Thinking
  176. 1,365 Gemma 3 27B
  177. 1,364 glm-4.7-flash
  178. 1,364 MiniMax-M1-80k
  179. 1,364 Grok-3 mini
  180. 1,364 o3-mini
  181. 1,363 amazon-nova-experimental-chat (11-10)
  182. 1,360 Gemini 2.0 Flash
  183. 1,360 Nemotron 3 Super
  184. 1,358 DeepSeek-V3
  185. 1,356 Mistral Small 3.2
  186. 1,356 INTELLECT-3
  187. 1,354 Cohere Command A
  188. 1,354 Gemini 2.0 Flash-Lite
  189. 1,352 GLM-4.5V
  190. 1,352 gpt-oss-120b
  191. 1,351 Nemotron 3.5 Lightning 30B-A3B
  192. 1,351 Gemini 1.5 Pro
  193. 1,349 Step 3
  194. 1,348 amazon-nova-experimental-chat (10-20)
  195. 1,348 Llama-3.1-Nemotron-Ultra-253B-v1
  196. 1,347 Qwen3-32B
  197. 1,346 GPT-4o
  198. 1,346 amazon-nova-experimental-chat (10-09)
  199. 1,346 Qwen-Plus (0125)
  200. 1,344 MiniMax-M2
  201. 1,343 Claude 3.5 Sonnet
  202. 1,343 Llama-3.3-Nemotron-Super-49B-v1.5
  203. 1,343 Ling-flash-2.0
  204. 1,343 Mercury 2
  205. 1,343 GLM-4-Plus (0111)
  206. 1,342 Gemma 3 12B
  207. 1,341 Hunyuan Turbo (0110)
  208. 1,340 Granite 4.2 30B
  209. 1,338 GPT-5 nano
  210. 1,337 o1-mini
  211. 1,336 Gemini Advanced (0514)
  212. 1,336 Grok-2
  213. 1,336 GPT-4o
  214. 1,336 QwQ-32B
  215. 1,335 Llama 3.1-405B
  216. 1,335 Nova 2 Lite
  217. 1,334 Step-2 16K Exp (202412)
  218. 1,329 Olmo 3.1 32B Instruct
  219. 1,328 Yi-Lightning
  220. 1,328 Llama-3.3-Nemotron-Super-49B-v1
  221. 1,327 Llama 4 Maverick
  222. 1,326 Qwen3-30B-A3B
  223. 1,326 Hunyuan Large 20250210
  224. 1,325 Claude 3.5 Haiku
  225. 1,325 GPT-4 Turbo
  226. 1,324 Gemini 1.5 Pro
  227. 1,323 DeepSeek-V2.5-1210
  228. 1,322 Ring-flash-2.0
  229. 1,322 GPT-4.1 nano
  230. 1,322 Claude 3 Opus
  231. 1,322 Llama 4 Scout
  232. 1,321 Molmo2-8B
  233. 1,320 Step-1o Turbo (202506)
  234. 1,319 GLM-4-Plus
  235. 1,318 Qwen-Max (0919)
  236. 1,318 Llama 3.3 70B Instruct
  237. 1,318 GPT-4o mini
  238. 1,318 gpt-oss-20b
  239. 1,317 Gemma 3n E4B
  240. 1,315 Qwen2.5-Plus (1127)
  241. 1,314 Mistral Large 2
  242. 1,314 Athene-V2-Chat
  243. 1,314 Nemotron 3 Nano 30B-A3B
  244. 1,313 GPT-4 Turbo (Jan 2024)
  245. 1,313 GPT-4 Turbo
  246. 1,311 Hunyuan Standard 20250210
  247. 1,309 Gemini 1.5 Flash
  248. 1,308 Grok-2 mini
  249. 1,307 DeepSeek-V2.5
  250. 1,307 Athene-70B
  251. 1,306 Olmo 3 32B Think
  252. 1,306 Mistral Large 2
  253. 1,305 Mercury
  254. 1,305 Magistral Medium 1.0
  255. 1,304 Granite 4.1 8B
  256. 1,303 Gemma 3 4B
  257. 1,303 Qwen2.5-72B
  258. 1,303 Mistral Small 3.1
  259. 1,299 Llama-3.1-Nemotron-70B-Instruct
  260. 1,294 Hunyuan Large Vision
  261. 1,293 Llama 3.1-70B
  262. 1,290 Amazon Nova Pro
  263. 1,290 Gemma 2 27B
  264. 1,290 Granite 4.2 8B
  265. 1,290 Jamba 1.5 Large
  266. 1,289 Granite 4.2 3B
  267. 1,288 Reka Core
  268. 1,288 GPT-4
  269. 1,287 Granite 4.0 H Small
  270. 1,287 Llama-3.1-Nemotron-51B-Instruct
  271. 1,287 Gemini 1.5 Flash
  272. 1,286 Tulu 3 (Tülu 3) 70B
  273. 1,286 Olmo 3.1 32B Think
  274. 1,281 Claude 3 Sonnet
  275. 1,280 Gemma 2 9B IT SimPO
  276. 1,277 Nemotron-4-340B-Instruct
  277. 1,277 Llama 3-70B
  278. 1,276 GPT-4
  279. 1,276 Command R+
  280. 1,274 Mistral Small 3
  281. 1,273 GLM-4 (0520)
  282. 1,273 Reka Flash
  283. 1,271 Qwen2.5-Coder-32B-Instruct
  284. 1,267 Aya Expanse 32B
  285. 1,267 Gemma 2 9B
  286. 1,266 DeepSeek-Coder-V2 236B
  287. 1,262 Qwen2-72B
  288. 1,262 Claude 3 Haiku
  289. 1,260 Amazon Nova Lite
  290. 1,259 Gemini 1.5 Flash 8B
  291. 1,256 Phi-4
  292. 1,252 OLMo 2 32B Instruct
  293. 1,251 c4ai-command-r-08-2024
  294. 1,243 Mistral Large
  295. 1,241 Amazon Nova Micro
  296. 1,240 Jamba 1.5 Mini
  297. 1,238 Ministral 8B
  298. 1,237 Gemini 1.0 Pro
  299. 1,234 Qwen1.5-110B
  300. 1,234 Qwen1.5-72B
  301. 1,234 Reka Flash 21B (Online)
  302. 1,233 Hunyuan Standard 256K
  303. 1,230 Mixtral 8x22B
  304. 1,227 Command R (03-2024)
  305. 1,226 GPT-3.5 Turbo
  306. 1,224 Llama 3-8B
  307. 1,223 Aya Expanse 8B
  308. 1,223 Mistral Medium
  309. 1,221 Llama-3.1-Tulu-3-8B
  310. 1,213 Zephyr ORPO 141B A35B v0.1
  311. 1,213 Yi-1.5-34B
  312. 1,211 Llama 3.1-8B
  313. 1,209 Granite-3.1-8B-Instruct
  314. 1,204 GPT-3.5 Turbo
  315. 1,204 Qwen1.5-32B
  316. 1,200 Gemma 2 2B IT
  317. 1,198 phi-3-medium 14B
  318. 1,197 Mixtral 8x7B
  319. 1,196 DBRX
  320. 1,191 Qwen1.5-14B
  321. 1,191 InternLM2.5-20B-Chat
  322. 1,185 DeepSeek LLM 67B
  323. 1,185 WizardLM 70B
  324. 1,184 Yi-34B
  325. 1,183 Granite-3.0-8B-Instruct
  326. 1,183 OpenChat 3.5
  327. 1,183 OpenChat 3.5 (0106)
  328. 1,183 Gemma 1.1 7B IT
  329. 1,180 Snowflake Arctic Instruct
  330. 1,179 Granite-3.1-2B-Instruct
  331. 1,178 Tulu 2 DPO 70B
  332. 1,176 OpenHermes 2.5 Mistral 7B
  333. 1,173 Vicuna 33B
  334. 1,171 phi-3-small 7.4B
  335. 1,171 Starling-LM-7B-beta
  336. 1,171 Llama 2-70B
  337. 1,168 Starling-LM-7B-alpha
  338. 1,167 Llama 3.2 3B
  339. 1,164 Nous-Hermes-2-Mixtral-8x7B-DPO
  340. 1,157 Granite-3.0-2B-Instruct
  341. 1,155 Llama2-70B-SteerLM-Chat
  342. 1,154 QwQ-32B-Preview
  343. 1,153 SOLAR-10.7B-Instruct-v1.0
  344. 1,152 Dolphin 2.2.1 Mistral 7B
  345. 1,151 MPT-30B
  346. 1,150 WizardLM 13B
  347. 1,149 Mistral 7B v0.2
  348. 1,148 Falcon-180B
  349. 1,144 Qwen1.5-7B
  350. 1,143 Phi-3 Mini 4K Instruct (June 2024)
  351. 1,142 Vicuna 13B
  352. 1,142 Llama 2-13B
  353. 1,140 Qwen-14B
  354. 1,139 PaLM 2
  355. 1,138 Gemma 7B
  356. 1,137 Code Llama 34B Instruct
  357. 1,131 Zephyr 7B Beta
  358. 1,130 Phi-3-mini-128k-instruct
  359. 1,128 phi-3-mini 3.8B
  360. 1,128 Guanaco 33B
  361. 1,127 Zephyr 7B Alpha
  362. 1,122 StripedHyena Nous 7B
  363. 1,119 Code Llama 70B Instruct
  364. 1,117 Gemma 1.1 2B IT
  365. 1,115 Vicuna 7B
  366. 1,115 SmolLM2 1.7B Instruct
  367. 1,111 Llama 3.2 1B
  368. 1,111 Mistral-7B-Instruct-v0.1
  369. 1,108 Llama 2-7B
  370. 1,094 Gemma 2B
  371. 1,091 Qwen1.5-4B-Chat
  372. 1,074 OLMo-7B-Instruct
  373. 1,071 Koala 13B
  374. 1,070 Alpaca 13B
  375. 1,068 GPT4All 13B Snoozy
  376. 1,064 MPT-7B
  377. 1,057 ChatGLM3-6B
  378. 1,042 RWKV-4 Raven 14B
  379. 1,025 chatglm2-6b
  380. 1,024 OpenAssistant Pythia 12B
  381. 996 ChatGLM-6B
  382. 993 FastChat-T5-3B
  383. 983 Dolly 2.0-12b
  384. 975 LLaMA-13B
  385. 953 stablelm-tuned-alpha-7b

Bars start at 800.

  1. 1 Gemini 4 Carbon high 1,526
  2. 2 Gemini 4 Argon high 1,522
  3. 3 Muse Wonder max 1,511
  4. 4 Claude Opus 5.5 high 1,506
  5. 5 Claude Fable 5 high 1,504
  6. 6 Claude Opus 4.6 high 1,503
  7. 7 Claude Fable 5.1 max 1,503
  8. 8 Claude Opus 4.7 high 1,501
  9. 9 Gemini 3.8 Flash high 1,497
  10. 10 Muse Spark 1.3 max 1,496
  11. 11 Muse Spark 1.2 xhigh 1,493
  12. 12 Muse Spark 1.1 1,491
  13. 13 Claude Opus 5 high 1,490
  14. 14 Gemini 3.7 Flash high 1,489
  15. 15 Muse Spark 1,489
  16. 16 Kimi K3 max 1,487
  17. 17 Gemini 3.1 Pro 1,487
  18. 18 Gemini 3 Pro 1,486
  19. 19 GPT-5.6 Sol xhigh 1,485
  20. 20 Qwen 3.8 Max 1,484
  21. 21 Kimi K3.1 Pro max 1,483
  22. 22 Gemini 3.6 Flash high 1,483
  23. 23 GLM-5.3 max 1,483
  24. 24 GPT-6.1 Sol max 1,482
  25. 25 Claude Opus 4.8 high 1,482
  26. 26 GPT-5.5 high 1,481
  27. 27 MiMo-V2.6 Pro 1,480
  28. 28 Gemini 3.5 Flash high 1,478
  29. 29 GPT-5.2 Instant 1,476
  30. 30 GPT-5.4 high 1,475
  31. 31 GLM-5.2 max 1,475
  32. 32 DeepSeek V4.1 Flash max 1,475
  33. 33 Grok 4.20 Beta 1 1,475
  34. 34 GLM-5.3-Flash 1,474
  35. 35 GPT-6 Astra max 1,474
  36. 36 Qwen3.7-Max 1,474
  37. 37 Claude Opus 4.5 high, 32k 1,474
  38. 38 GPT-5.5 Instant 1,473
  39. 39 Gemini 3 Flash 1,473
  40. 40 Claude Sonnet 5.5 xhigh 1,472
  41. 41 Grok 4.20 Beta (Reasoning, 0309) 1,472
  42. 42 Claude Sonnet 4.6 1,472
  43. 43 Grok 4.20 Multi-Agent Beta (0309) 1,471
  44. 44 GPT-5.6 Terra xhigh 1,468
  45. 45 ERNIE 5.1 1,467
  46. 46 MiMo-V2.5-Pro 1,467
  47. 47 Grok 4.5 1,466
  48. 48 Grok 4.1 thinking 1,465
  49. 49 GLM-5.1 1,465
  50. 50 Qwen3.5-Max-Preview 1,465
  51. 51 DeepSeek-V4-Pro high 1,464
  52. 52 Claude Sonnet 5 high 1,461
  53. 53 Kimi K2.6 1,461
  54. 54 Qwen 3.6 Max (Preview) 1,460
  55. 55 GLM-5 1,457
  56. 56 GPT-6 Sol max 1,457
  57. 57 Seed2.0 Pro 1,457
  58. 58 Grok 4.6 high 1,456
  59. 59 Claude Sonnet 4.5 high, 32k 1,456
  60. 60 GPT-5.1 high 1,455
  61. 61 Qwen3.7-Plus 1,455
  62. 62 Gemini 3.5 Flash-Lite 1,455
  63. 63 Tencent Hy3 1,454
  64. 64 GPT-5.6 Luna xhigh 1,453
  65. 65 Gemma 4 31B IT 1,452
  66. 66 GPT-5.3 Instant 1,450
  67. 67 Claude Opus 4.1 thinking 16k 1,450
  68. 68 Kimi K2.5 thinking 1,450
  69. 69 ERNIE-5.0-Preview (1203) 1,449
  70. 70 Step 5 Preview 1,448
  71. 71 MiMo-V2-Pro 1,448
  72. 72 MiMo-V2.6 Flash 1,448
  73. 73 GPT-5.4 Mini high 1,447
  74. 74 ERNIE 5.0 (0110) 1,446
  75. 75 Gemini 2.5 Pro Jun 2025 1,446
  76. 76 GPT-4.5 1,445
  77. 77 Inkling 1,443
  78. 78 Qwen 3.6 Plus 1,443
  79. 79 GPT-4o Mar 2025 1,443
  80. 80 Grok 4.7 xhigh 1,442
  81. 81 Grok 4.3 1,442
  82. 82 Qwen3.5 397B-A17B 1,441
  83. 83 GLM-4.7 1,441
  84. 84 GPT-6 Luna max 1,441
  85. 85 DeepSeek-V4-Flash high 1,439
  86. 86 Gemma 4 26B A4B 1,437
  87. 87 GPT-5.2 high 1,437
  88. 88 LongCat-Flash-Chat Exp (2602) 1,436
  89. 89 MiniMax-M3 1,436
  90. 90 GPT-5 high 1,435
  91. 91 Beam 1.0 1,435
  92. 92 Qwen3-Max 1,434
  93. 93 GLM-5V-Turbo 1,434
  94. 94 MiMo-V2.5 1,434
  95. 95 Qwen 3.8 27B 1,433
  96. 96 Gemini 3.1 Flash-Lite 1,433
  97. 97 o3 1,432
  98. 98 Grok 4.1 Fast reasoning 1,431
  99. 99 MiMo-V2-Omni 1,430
  100. 100 Kimi K2 Thinking Turbo 1,430
  101. 101 GPT-5 Chat 1,427
  102. 102 amazon-nova-experimental-chat (26-02-10) 1,427
  103. 103 Mistral Medium 3.5 1,427
  104. 104 Nemotron 3 Ultra nvfp4 1,426
  105. 105 Claude Opus 4 thinking 16k 1,426
  106. 106 DeepSeek-V3.2-Exp thinking 1,425
  107. 107 DeepSeek-V3.2 1,425
  108. 108 Muse Glimmer 1,425
  109. 109 GLM-4.6 1,424
  110. 110 Mistral Large 4 1,423
  111. 111 Claude Haiku 5.5 high 1,422
  112. 112 Qwen3-235B-A22B-Instruct Jul 2025 1,422
  113. 113 DeepSeek-R1 May 2025 1,421
  114. 114 Grok 4 Fast non-reasoning 1,418
  115. 115 Kimi K2 Sep 2025 1,418
  116. 116 ERNIE-5.0-Preview (1022) 1,418
  117. 117 Kimi K2 Jul 2025 1,418
  118. 118 DeepSeek-V3.1 1,417
  119. 119 Qwen3.5-122B-A10B 1,416
  120. 120 DeepSeek-V3.1-Terminus thinking 1,416
  121. 121 Nemotron 3.5 Super VL nvfp4 1,415
  122. 122 MiniMax-M2.7 1,415
  123. 123 Mistral Large 3 1,415
  124. 124 GPT-4.1 1,415
  125. 125 Claude Haiku 4.5 1,414
  126. 126 Qwen3-VL-235B-A22B-Instruct 1,413
  127. 127 Inkling 2 Small 1,412
  128. 128 amazon-nova-experimental-chat (26-01-10) 1,412
  129. 129 Grok 3 1,411
  130. 130 GLM-4.5 1,411
  131. 131 Grok 4 1,411
  132. 132 Gemini 2.5 Flash Jun 2025 1,409
  133. 133 Tencent Hy3 preview 1,409
  134. 134 Qwen3.5-27B 1,409
  135. 135 Mistral Medium 3.1 1,408
  136. 136 Inkling-Small 1,405
  137. 137 Gemini 2.5 Flash Sep 2025 1,403
  138. 138 o1 1,402
  139. 139 Qwen3-235B-A22B non-thinking 1,402
  140. 140 Claude Sonnet 4 thinking 32k 1,402
  141. 141 GPT-5.4 Nano high 1,401
  142. 142 LongCat-Flash-Chat 1,400
  143. 143 Qwen3-235B-A22B-Thinking Jul 2025 1,400
  144. 144 Qwen3-Next-80B-A3B-Instruct 1,399
  145. 145 DeepSeek-R1 1,398
  146. 146 Qwen3.5-Flash 1,396
  147. 147 DeepSeek-V3 Mar 2025 1,395
  148. 148 Qwen3-VL-235B-A22B thinking 1,395
  149. 149 Hunyuan Vision 1.5 Thinking 1,394
  150. 150 Qwen3.5-35B-A3B 1,394
  151. 151 Step 3.5 Flash 1,393
  152. 152 amazon-nova-experimental-chat (12-10) 1,393
  153. 153 MiMo-V2-Flash non-thinking 1,392
  154. 154 o4-mini 1,391
  155. 155 MiniMax-M2.5 1,391
  156. 156 GPT-5 mini high 1,390
  157. 157 o1-preview 1,389
  158. 158 Claude 3.7 Sonnet thinking 32k 1,388
  159. 159 Qwen3-Coder-480B-A35B 1,388
  160. 160 Solar Pro 4 1,387
  161. 161 Hunyuan-T1 1,387
  162. 162 Mistral Medium 3 1,387
  163. 163 MiniMax-M2.1 1,384
  164. 164 Hunyuan-TurboS 1,383
  165. 165 GPT-4.1 mini 1,383
  166. 166 Qwen3-30B-A3B-Instruct Jul 2025 1,382
  167. 167 Gemini 2.5 Flash-Lite Sep 2025, non-thinking, 09-2025 1,379
  168. 168 Trinity Large Preview 1,379
  169. 169 GLM-4.6V 1,378
  170. 170 Gemini 2.5 Flash-Lite Jun 2025 1,375
  171. 171 Claude 3.5 Sonnet (October 2024) 1,374
  172. 172 Qwen2.5-Max 1,374
  173. 173 GLM-4.5-Air 1,373
  174. 174 Qwen3-Next-80B-A3B thinking 1,369
  175. 175 Trinity Large Thinking 1,367
  176. 176 Gemma 3 27B 1,365
  177. 177 glm-4.7-flash 1,364
  178. 178 MiniMax-M1-80k 1,364
  179. 179 Grok-3 mini high 1,364
  180. 180 o3-mini high 1,364
  181. 181 amazon-nova-experimental-chat (11-10) 1,363
  182. 182 Gemini 2.0 Flash Feb 2025 1,360
  183. 183 Nemotron 3 Super 1,360
  184. 184 DeepSeek-V3 1,358
  185. 185 Mistral Small 3.2 1,356
  186. 186 INTELLECT-3 1,356
  187. 187 Cohere Command A 1,354
  188. 188 Gemini 2.0 Flash-Lite 1,354
  189. 189 GLM-4.5V 1,352
  190. 190 gpt-oss-120b 1,352
  191. 191 Nemotron 3.5 Lightning 30B-A3B nvfp4 1,351
  192. 192 Gemini 1.5 Pro Sep 2024 1,351
  193. 193 Step 3 1,349
  194. 194 amazon-nova-experimental-chat (10-20) 1,348
  195. 195 Llama-3.1-Nemotron-Ultra-253B-v1 1,348
  196. 196 Qwen3-32B 1,347
  197. 197 GPT-4o May 2024 1,346
  198. 198 amazon-nova-experimental-chat (10-09) 1,346
  199. 199 Qwen-Plus (0125) 1,346
  200. 200 MiniMax-M2 1,344
  201. 201 Claude 3.5 Sonnet 1,343
  202. 202 Llama-3.3-Nemotron-Super-49B-v1.5 1,343
  203. 203 Ling-flash-2.0 1,343
  204. 204 Mercury 2 1,343
  205. 205 GLM-4-Plus (0111) 1,343
  206. 206 Gemma 3 12B 1,342
  207. 207 Hunyuan Turbo (0110) 1,341
  208. 208 Granite 4.2 30B 1,340
  209. 209 GPT-5 nano high 1,338
  210. 210 o1-mini 1,337
  211. 211 Gemini Advanced (0514) 1,336
  212. 212 Grok-2 Aug 2024 1,336
  213. 213 GPT-4o Aug 2024 1,336
  214. 214 QwQ-32B 1,336
  215. 215 Llama 3.1-405B bf16 1,335
  216. 216 Nova 2 Lite 1,335
  217. 217 Step-2 16K Exp (202412) 1,334
  218. 218 Olmo 3.1 32B Instruct 1,329
  219. 219 Yi-Lightning 1,328
  220. 220 Llama-3.3-Nemotron-Super-49B-v1 1,328
  221. 221 Llama 4 Maverick 1,327
  222. 222 Qwen3-30B-A3B 1,326
  223. 223 Hunyuan Large 20250210 1,326
  224. 224 Claude 3.5 Haiku 1,325
  225. 225 GPT-4 Turbo Apr 2024 1,325
  226. 226 Gemini 1.5 Pro May 2024 1,324
  227. 227 DeepSeek-V2.5-1210 1,323
  228. 228 Ring-flash-2.0 1,322
  229. 229 GPT-4.1 nano 1,322
  230. 230 Claude 3 Opus 1,322
  231. 231 Llama 4 Scout 1,322
  232. 232 Molmo2-8B 1,321
  233. 233 Step-1o Turbo (202506) 1,320
  234. 234 GLM-4-Plus 1,319
  235. 235 Qwen-Max (0919) 1,318
  236. 236 Llama 3.3 70B Instruct 1,318
  237. 237 GPT-4o mini 1,318
  238. 238 gpt-oss-20b 1,318
  239. 239 Gemma 3n E4B 1,317
  240. 240 Qwen2.5-Plus (1127) 1,315
  241. 241 Mistral Large 2 Jul 2024 1,314
  242. 242 Athene-V2-Chat 1,314
  243. 243 Nemotron 3 Nano 30B-A3B bf16 1,314
  244. 244 GPT-4 Turbo (Jan 2024) 1,313
  245. 245 GPT-4 Turbo Nov 2023 1,313
  246. 246 Hunyuan Standard 20250210 1,311
  247. 247 Gemini 1.5 Flash Sep 2024 1,309
  248. 248 Grok-2 mini 1,308
  249. 249 DeepSeek-V2.5 Sep 2024 1,307
  250. 250 Athene-70B 1,307
  251. 251 Olmo 3 32B Think 1,306
  252. 252 Mistral Large 2 Nov 2024 1,306
  253. 253 Mercury 1,305
  254. 254 Magistral Medium 1.0 1,305
  255. 255 Granite 4.1 8B 1,304
  256. 256 Gemma 3 4B 1,303
  257. 257 Qwen2.5-72B 1,303
  258. 258 Mistral Small 3.1 1,303
  259. 259 Llama-3.1-Nemotron-70B-Instruct 1,299
  260. 260 Hunyuan Large Vision 1,294
  261. 261 Llama 3.1-70B 1,293
  262. 262 Amazon Nova Pro 1,290
  263. 263 Gemma 2 27B 1,290
  264. 264 Granite 4.2 8B 1,290
  265. 265 Jamba 1.5 Large 1,290
  266. 266 Granite 4.2 3B 1,289
  267. 267 Reka Core 1,288
  268. 268 GPT-4 Mar 2023 1,288
  269. 269 Granite 4.0 H Small 1,287
  270. 270 Llama-3.1-Nemotron-51B-Instruct 1,287
  271. 271 Gemini 1.5 Flash May 2024 1,287
  272. 272 Tulu 3 (Tülu 3) 70B 1,286
  273. 273 Olmo 3.1 32B Think 1,286
  274. 274 Claude 3 Sonnet 1,281
  275. 275 Gemma 2 9B IT SimPO 1,280
  276. 276 Nemotron-4-340B-Instruct 1,277
  277. 277 Llama 3-70B 1,277
  278. 278 GPT-4 Jun 2023 1,276
  279. 279 Command R+ 1,276
  280. 280 Mistral Small 3 1,274
  281. 281 GLM-4 (0520) 1,273
  282. 282 Reka Flash 1,273
  283. 283 Qwen2.5-Coder-32B-Instruct 1,271
  284. 284 Aya Expanse 32B 1,267
  285. 285 Gemma 2 9B 1,267
  286. 286 DeepSeek-Coder-V2 236B 1,266
  287. 287 Qwen2-72B 1,262
  288. 288 Claude 3 Haiku 1,262
  289. 289 Amazon Nova Lite 1,260
  290. 290 Gemini 1.5 Flash 8B 1,259
  291. 291 Phi-4 1,256
  292. 292 OLMo 2 32B Instruct 1,252
  293. 293 c4ai-command-r-08-2024 1,251
  294. 294 Mistral Large 1,243
  295. 295 Amazon Nova Micro 1,241
  296. 296 Jamba 1.5 Mini 1,240
  297. 297 Ministral 8B 1,238
  298. 298 Gemini 1.0 Pro 1,237
  299. 299 Qwen1.5-110B 1,234
  300. 300 Qwen1.5-72B 1,234
  301. 301 Reka Flash 21B (Online) 1,234
  302. 302 Hunyuan Standard 256K 1,233
  303. 303 Mixtral 8x22B 1,230
  304. 304 Command R (03-2024) 1,227
  305. 305 GPT-3.5 Turbo Jan 2024 1,226
  306. 306 Llama 3-8B 1,224
  307. 307 Aya Expanse 8B 1,223
  308. 308 Mistral Medium 1,223
  309. 309 Llama-3.1-Tulu-3-8B 1,221
  310. 310 Zephyr ORPO 141B A35B v0.1 1,213
  311. 311 Yi-1.5-34B 1,213
  312. 312 Llama 3.1-8B 1,211
  313. 313 Granite-3.1-8B-Instruct 1,209
  314. 314 GPT-3.5 Turbo Nov 2023 1,204
  315. 315 Qwen1.5-32B 1,204
  316. 316 Gemma 2 2B IT 1,200
  317. 317 phi-3-medium 14B 1,198
  318. 318 Mixtral 8x7B 1,197
  319. 319 DBRX 1,196
  320. 320 Qwen1.5-14B 1,191
  321. 321 InternLM2.5-20B-Chat 1,191
  322. 322 DeepSeek LLM 67B 1,185
  323. 323 WizardLM 70B 1,185
  324. 324 Yi-34B 1,184
  325. 325 Granite-3.0-8B-Instruct 1,183
  326. 326 OpenChat 3.5 1,183
  327. 327 OpenChat 3.5 (0106) 1,183
  328. 328 Gemma 1.1 7B IT 1,183
  329. 329 Snowflake Arctic Instruct 1,180
  330. 330 Granite-3.1-2B-Instruct 1,179
  331. 331 Tulu 2 DPO 70B 1,178
  332. 332 OpenHermes 2.5 Mistral 7B 1,176
  333. 333 Vicuna 33B 1,173
  334. 334 phi-3-small 7.4B 1,171
  335. 335 Starling-LM-7B-beta 1,171
  336. 336 Llama 2-70B 1,171
  337. 337 Starling-LM-7B-alpha 1,168
  338. 338 Llama 3.2 3B 1,167
  339. 339 Nous-Hermes-2-Mixtral-8x7B-DPO 1,164
  340. 340 Granite-3.0-2B-Instruct 1,157
  341. 341 Llama2-70B-SteerLM-Chat 1,155
  342. 342 QwQ-32B-Preview 1,154
  343. 343 SOLAR-10.7B-Instruct-v1.0 1,153
  344. 344 Dolphin 2.2.1 Mistral 7B 1,152
  345. 345 MPT-30B 1,151
  346. 346 WizardLM 13B 1,150
  347. 347 Mistral 7B v0.2 1,149
  348. 348 Falcon-180B 1,148
  349. 349 Qwen1.5-7B 1,144
  350. 350 Phi-3 Mini 4K Instruct (June 2024) 1,143
  351. 351 Vicuna 13B 1,142
  352. 352 Llama 2-13B 1,142
  353. 353 Qwen-14B 1,140
  354. 354 PaLM 2 1,139
  355. 355 Gemma 7B 1,138
  356. 356 Code Llama 34B Instruct 1,137
  357. 357 Zephyr 7B Beta 1,131
  358. 358 Phi-3-mini-128k-instruct 1,130
  359. 359 phi-3-mini 3.8B 1,128
  360. 360 Guanaco 33B 1,128
  361. 361 Zephyr 7B Alpha 1,127
  362. 362 StripedHyena Nous 7B 1,122
  363. 363 Code Llama 70B Instruct 1,119
  364. 364 Gemma 1.1 2B IT 1,117
  365. 365 Vicuna 7B 1,115
  366. 366 SmolLM2 1.7B Instruct 1,115
  367. 367 Llama 3.2 1B 1,111
  368. 368 Mistral-7B-Instruct-v0.1 1,111
  369. 369 Llama 2-7B 1,108
  370. 370 Gemma 2B 1,094
  371. 371 Qwen1.5-4B-Chat 1,091
  372. 372 OLMo-7B-Instruct 1,074
  373. 373 Koala 13B 1,071
  374. 374 Alpaca 13B 1,070
  375. 375 GPT4All 13B Snoozy 1,068
  376. 376 MPT-7B 1,064
  377. 377 ChatGLM3-6B 1,057
  378. 378 RWKV-4 Raven 14B 1,042
  379. 379 chatglm2-6b 1,025
  380. 380 OpenAssistant Pythia 12B 1,024
  381. 381 ChatGLM-6B 996
  382. 382 FastChat-T5-3B 993
  383. 383 Dolly 2.0-12b 983
  384. 384 LLaMA-13B 975
  385. 385 stablelm-tuned-alpha-7b 953

Source: Official LMArena (Elo) leaderboard

336 models. Scroll sideways for the rest. Bars start at 800.

  1. 1,526 Gemini 4 Carbon
  2. 1,522 Gemini 4 Argon
  3. 1,511 Muse Wonder
  4. 1,506 Claude Opus 5.5
  5. 1,504 Claude Fable 5
  6. 1,503 Claude Opus 4.6
  7. 1,503 Claude Fable 5.1
  8. 1,501 Claude Opus 4.7
  9. 1,497 Gemini 3.8 Flash
  10. 1,496 Muse Spark 1.3
  11. 1,493 Muse Spark 1.2
  12. 1,491 Muse Spark 1.1
  13. 1,490 Claude Opus 5
  14. 1,489 Gemini 3.7 Flash
  15. 1,489 Muse Spark
  16. 1,487 Kimi K3
  17. 1,487 Gemini 3.1 Pro
  18. 1,486 Gemini 3 Pro
  19. 1,485 GPT-5.6 Sol
  20. 1,484 Qwen 3.8 Max
  21. 1,483 Kimi K3.1 Pro
  22. 1,483 Grok 4.1
  23. 1,483 Gemini 3.6 Flash
  24. 1,483 GLM-5.3
  25. 1,482 GPT-6.1 Sol
  26. 1,482 Claude Opus 4.8
  27. 1,481 GPT-5.5
  28. 1,480 MiMo-V2.6 Pro
  29. 1,478 Gemini 3.5 Flash
  30. 1,476 GPT-5.2 Instant
  31. 1,475 GPT-5.4
  32. 1,475 GLM-5.2
  33. 1,475 DeepSeek V4.1 Flash
  34. 1,474 GLM-5.3-Flash
  35. 1,474 GPT-6 Astra
  36. 1,474 Qwen3.7-Max
  37. 1,474 Claude Opus 4.5
  38. 1,473 GPT-5.5 Instant
  39. 1,473 Gemini 3 Flash
  40. 1,472 Claude Sonnet 5.5
  41. 1,472 Claude Sonnet 4.6
  42. 1,468 GPT-5.6 Terra
  43. 1,467 ERNIE 5.1
  44. 1,467 MiMo-V2.5-Pro
  45. 1,466 Grok 4.5
  46. 1,465 GLM-5.1
  47. 1,464 DeepSeek-V4-Pro
  48. 1,461 Claude Sonnet 5
  49. 1,461 Kimi K2.6
  50. 1,460 Qwen 3.6 Max (Preview)
  51. 1,457 GLM-5
  52. 1,457 GPT-6 Sol
  53. 1,457 Seed2.0 Pro
  54. 1,456 Grok 4.6
  55. 1,456 Claude Sonnet 4.5
  56. 1,455 GPT-5.1
  57. 1,455 Qwen3.7-Plus
  58. 1,455 Gemini 3.5 Flash-Lite
  59. 1,454 Tencent Hy3
  60. 1,453 GPT-5.6 Luna
  61. 1,452 Gemma 4 31B IT
  62. 1,450 GPT-5.3 Instant
  63. 1,450 Claude Opus 4.1
  64. 1,450 Kimi K2.5
  65. 1,448 Step 5 Preview
  66. 1,448 MiMo-V2-Pro
  67. 1,448 MiMo-V2.6 Flash
  68. 1,447 GPT-5.4 Mini
  69. 1,446 Gemini 2.5 Pro
  70. 1,445 GPT-4.5
  71. 1,443 Inkling
  72. 1,443 Qwen 3.6 Plus
  73. 1,443 GPT-4o
  74. 1,442 Grok 4.7
  75. 1,442 Grok 4.3
  76. 1,441 Qwen3.5 397B-A17B
  77. 1,441 GLM-4.7
  78. 1,441 GPT-6 Luna
  79. 1,439 DeepSeek-V4-Flash
  80. 1,438 Gemma 4 26B A4B
  81. 1,437 GPT-5.2
  82. 1,436 MiniMax-M3
  83. 1,435 GPT-5
  84. 1,435 Beam 1.0
  85. 1,434 Qwen3-Max
  86. 1,434 GLM-5V-Turbo
  87. 1,434 MiMo-V2.5
  88. 1,433 Qwen 3.8 27B
  89. 1,433 Gemini 3.1 Flash-Lite
  90. 1,432 o3
  91. 1,431 Grok 4.1 Fast
  92. 1,430 MiMo-V2-Omni
  93. 1,427 GPT-5 Chat
  94. 1,427 Mistral Medium 3.5
  95. 1,426 Nemotron 3 Ultra
  96. 1,426 Claude Opus 4
  97. 1,425 DeepSeek-V3.2-Exp
  98. 1,425 DeepSeek-V3.2
  99. 1,425 Muse Glimmer
  100. 1,424 GLM-4.6
  101. 1,423 Mistral Large 4
  102. 1,422 Claude Haiku 5.5
  103. 1,422 Qwen3-235B-A22B-Instruct
  104. 1,421 DeepSeek-R1
  105. 1,420 Nemotron 3.5 Super VL
  106. 1,418 Grok 4 Fast
  107. 1,418 Kimi K2
  108. 1,418 Mistral Large 3
  109. 1,418 Kimi K2
  110. 1,417 DeepSeek-V3.1
  111. 1,416 Qwen3.5-122B-A10B
  112. 1,416 DeepSeek-V3.1-Terminus
  113. 1,415 MiniMax-M2.7
  114. 1,415 GPT-4.1
  115. 1,414 Claude Haiku 4.5
  116. 1,413 Qwen3-VL-235B-A22B-Instruct
  117. 1,412 Inkling 2 Small
  118. 1,411 Grok 3
  119. 1,411 GLM-4.5
  120. 1,411 Grok 4
  121. 1,409 Gemini 2.5 Flash
  122. 1,409 Tencent Hy3 preview
  123. 1,409 Qwen3.5-27B
  124. 1,408 Mistral Medium 3.1
  125. 1,405 Inkling-Small
  126. 1,403 Gemini 2.5 Flash
  127. 1,402 o1
  128. 1,402 Qwen3-235B-A22B
  129. 1,402 Claude Sonnet 4
  130. 1,401 GPT-5.4 Nano
  131. 1,400 LongCat-Flash-Chat
  132. 1,400 Qwen3-235B-A22B-Thinking
  133. 1,399 Qwen3-Next-80B-A3B-Instruct
  134. 1,398 DeepSeek-R1
  135. 1,396 Qwen3.5-Flash
  136. 1,395 DeepSeek-V3
  137. 1,395 Qwen3-VL-235B-A22B
  138. 1,394 Qwen3.5-35B-A3B
  139. 1,393 Step 3.5 Flash
  140. 1,392 MiMo-V2-Flash
  141. 1,391 o4-mini
  142. 1,391 MiniMax-M2.5
  143. 1,390 GPT-5 mini
  144. 1,389 o1-preview
  145. 1,388 Claude 3.7 Sonnet
  146. 1,388 Qwen3-Coder-480B-A35B
  147. 1,387 Solar Pro 4
  148. 1,387 Hunyuan-T1
  149. 1,387 Mistral Medium 3
  150. 1,384 MiniMax-M2.1
  151. 1,383 Hunyuan-TurboS
  152. 1,383 GPT-4.1 mini
  153. 1,382 Qwen3-30B-A3B-Instruct
  154. 1,379 Gemini 2.5 Flash-Lite
  155. 1,379 Trinity Large Preview
  156. 1,378 GLM-4.6V
  157. 1,375 Gemini 2.5 Flash-Lite
  158. 1,374 Claude 3.5 Sonnet (October 2024)
  159. 1,374 Qwen2.5-Max
  160. 1,373 GLM-4.5-Air
  161. 1,369 Qwen3-Next-80B-A3B
  162. 1,367 Trinity Large Thinking
  163. 1,365 Gemma 3 27B
  164. 1,364 glm-4.7-flash
  165. 1,364 MiniMax-M1-80k
  166. 1,364 Grok-3 mini
  167. 1,364 o3-mini
  168. 1,360 Gemini 2.0 Flash
  169. 1,360 Nemotron 3 Super
  170. 1,358 DeepSeek-V3
  171. 1,356 Mistral Small 3.2
  172. 1,356 INTELLECT-3
  173. 1,354 Cohere Command A
  174. 1,354 Gemini 2.0 Flash-Lite
  175. 1,352 GLM-4.5V
  176. 1,352 gpt-oss-120b
  177. 1,351 Nemotron 3.5 Lightning 30B-A3B
  178. 1,351 Gemini 1.5 Pro
  179. 1,349 Step 3
  180. 1,348 Llama-3.1-Nemotron-Ultra-253B-v1
  181. 1,347 Qwen3-32B
  182. 1,346 GPT-4o
  183. 1,344 MiniMax-M2
  184. 1,343 Claude 3.5 Sonnet
  185. 1,343 Llama-3.3-Nemotron-Super-49B-v1.5
  186. 1,343 Ling-flash-2.0
  187. 1,343 Mercury 2
  188. 1,342 Gemma 3 12B
  189. 1,340 Granite 4.2 30B
  190. 1,338 GPT-5 nano
  191. 1,337 o1-mini
  192. 1,336 Grok-2
  193. 1,336 GPT-4o
  194. 1,336 QwQ-32B
  195. 1,335 Llama 3.1-405B
  196. 1,335 Nova 2 Lite
  197. 1,329 Olmo 3.1 32B Instruct
  198. 1,328 Yi-Lightning
  199. 1,328 Llama-3.3-Nemotron-Super-49B-v1
  200. 1,327 Llama 4 Maverick
  201. 1,326 Qwen3-30B-A3B
  202. 1,325 Claude 3.5 Haiku
  203. 1,325 GPT-4 Turbo
  204. 1,324 Gemini 1.5 Pro
  205. 1,323 DeepSeek-V2.5-1210
  206. 1,322 Ring-flash-2.0
  207. 1,322 GPT-4.1 nano
  208. 1,322 Claude 3 Opus
  209. 1,322 Llama 4 Scout
  210. 1,321 Molmo2-8B
  211. 1,318 Llama 3.3 70B Instruct
  212. 1,318 GPT-4o mini
  213. 1,318 gpt-oss-20b
  214. 1,317 Gemma 3n E4B
  215. 1,314 Mistral Large 2
  216. 1,314 Athene-V2-Chat
  217. 1,314 Nemotron 3 Nano 30B-A3B
  218. 1,313 GPT-4 Turbo (Jan 2024)
  219. 1,313 GPT-4 Turbo
  220. 1,309 Gemini 1.5 Flash
  221. 1,308 Grok-2 mini
  222. 1,307 DeepSeek-V2.5
  223. 1,307 Athene-70B
  224. 1,306 Olmo 3 32B Think
  225. 1,306 Mistral Large 2
  226. 1,305 Mercury
  227. 1,305 Magistral Medium 1.0
  228. 1,304 Granite 4.1 8B
  229. 1,303 Gemma 3 4B
  230. 1,303 Qwen2.5-72B
  231. 1,303 Mistral Small 3.1
  232. 1,299 Llama-3.1-Nemotron-70B-Instruct
  233. 1,293 Llama 3.1-70B
  234. 1,290 Amazon Nova Pro
  235. 1,290 Gemma 2 27B
  236. 1,290 Granite 4.2 8B
  237. 1,290 Jamba 1.5 Large
  238. 1,289 Granite 4.2 3B
  239. 1,288 Reka Core
  240. 1,288 GPT-4
  241. 1,287 Granite 4.0 H Small
  242. 1,287 Llama-3.1-Nemotron-51B-Instruct
  243. 1,287 Gemini 1.5 Flash
  244. 1,286 Tulu 3 (Tülu 3) 70B
  245. 1,286 Olmo 3.1 32B Think
  246. 1,281 Claude 3 Sonnet
  247. 1,277 Nemotron-4-340B-Instruct
  248. 1,277 Llama 3-70B
  249. 1,276 GPT-4
  250. 1,276 Command R+
  251. 1,274 Mistral Small 3
  252. 1,273 Reka Flash
  253. 1,271 Qwen2.5-Coder-32B-Instruct
  254. 1,267 Aya Expanse 32B
  255. 1,267 Gemma 2 9B
  256. 1,266 DeepSeek-Coder-V2 236B
  257. 1,262 Qwen2-72B
  258. 1,262 Claude 3 Haiku
  259. 1,260 Amazon Nova Lite
  260. 1,259 Gemini 1.5 Flash 8B
  261. 1,256 Phi-4
  262. 1,252 OLMo 2 32B Instruct
  263. 1,251 c4ai-command-r-08-2024
  264. 1,243 Mistral Large
  265. 1,241 Amazon Nova Micro
  266. 1,240 Jamba 1.5 Mini
  267. 1,238 Ministral 8B
  268. 1,237 Gemini 1.0 Pro
  269. 1,234 Qwen1.5-110B
  270. 1,234 Qwen1.5-72B
  271. 1,230 Mixtral 8x22B
  272. 1,227 Command R (03-2024)
  273. 1,226 GPT-3.5 Turbo
  274. 1,224 Llama 3-8B
  275. 1,223 Aya Expanse 8B
  276. 1,223 Mistral Medium
  277. 1,221 Llama-3.1-Tulu-3-8B
  278. 1,213 Zephyr ORPO 141B A35B v0.1
  279. 1,213 Yi-1.5-34B
  280. 1,211 Llama 3.1-8B
  281. 1,209 Granite-3.1-8B-Instruct
  282. 1,204 GPT-3.5 Turbo
  283. 1,204 Qwen1.5-32B
  284. 1,200 Gemma 2 2B IT
  285. 1,198 phi-3-medium 14B
  286. 1,197 Mixtral 8x7B
  287. 1,196 DBRX
  288. 1,191 Qwen1.5-14B
  289. 1,191 InternLM2.5-20B-Chat
  290. 1,185 DeepSeek LLM 67B
  291. 1,184 Yi-34B
  292. 1,183 Granite-3.0-8B-Instruct
  293. 1,183 Gemma 1.1 7B IT
  294. 1,180 Snowflake Arctic Instruct
  295. 1,179 Granite-3.1-2B-Instruct
  296. 1,178 Tulu 2 DPO 70B
  297. 1,171 phi-3-small 7.4B
  298. 1,171 Starling-LM-7B-beta
  299. 1,171 Llama 2-70B
  300. 1,168 Starling-LM-7B-alpha
  301. 1,167 Llama 3.2 3B
  302. 1,164 Nous-Hermes-2-Mixtral-8x7B-DPO
  303. 1,157 Granite-3.0-2B-Instruct
  304. 1,155 Llama2-70B-SteerLM-Chat
  305. 1,154 QwQ-32B-Preview
  306. 1,153 SOLAR-10.7B-Instruct-v1.0
  307. 1,151 MPT-30B
  308. 1,149 Mistral 7B v0.2
  309. 1,148 Falcon-180B
  310. 1,144 Qwen1.5-7B
  311. 1,142 Llama 2-13B
  312. 1,140 Qwen-14B
  313. 1,138 Gemma 7B
  314. 1,137 Code Llama 34B Instruct
  315. 1,131 Zephyr 7B Beta
  316. 1,130 Phi-3-mini-128k-instruct
  317. 1,128 phi-3-mini 3.8B
  318. 1,127 Zephyr 7B Alpha
  319. 1,119 Code Llama 70B Instruct
  320. 1,117 Gemma 1.1 2B IT
  321. 1,115 SmolLM2 1.7B Instruct
  322. 1,111 Llama 3.2 1B
  323. 1,111 Mistral-7B-Instruct-v0.1
  324. 1,108 Llama 2-7B
  325. 1,094 Gemma 2B
  326. 1,091 Qwen1.5-4B-Chat
  327. 1,074 OLMo-7B-Instruct
  328. 1,064 MPT-7B
  329. 1,057 ChatGLM3-6B
  330. 1,031 Mistral 7B v0.1
  331. 1,025 chatglm2-6b
  332. 996 ChatGLM-6B
  333. 993 FastChat-T5-3B
  334. 983 Dolly 2.0-12b
  335. 975 LLaMA-13B
  336. 953 stablelm-tuned-alpha-7b

Bars start at 800.

  1. 1 Gemini 4 Carbon high 1,526
  2. 2 Gemini 4 Argon high 1,522
  3. 3 Muse Wonder max 1,511
  4. 4 Claude Opus 5.5 high 1,506
  5. 5 Claude Fable 5 high 1,504
  6. 6 Claude Opus 4.6 high 1,503
  7. 7 Claude Fable 5.1 max 1,503
  8. 8 Claude Opus 4.7 high 1,501
  9. 9 Gemini 3.8 Flash high 1,497
  10. 10 Muse Spark 1.3 max 1,496
  11. 11 Muse Spark 1.2 xhigh 1,493
  12. 12 Muse Spark 1.1 1,491
  13. 13 Claude Opus 5 high 1,490
  14. 14 Gemini 3.7 Flash high 1,489
  15. 15 Muse Spark 1,489
  16. 16 Kimi K3 max 1,487
  17. 17 Gemini 3.1 Pro 1,487
  18. 18 Gemini 3 Pro 1,486
  19. 19 GPT-5.6 Sol xhigh 1,485
  20. 20 Qwen 3.8 Max 1,484
  21. 21 Kimi K3.1 Pro max 1,483
  22. 22 Grok 4.1 1,483
  23. 23 Gemini 3.6 Flash high 1,483
  24. 24 GLM-5.3 max 1,483
  25. 25 GPT-6.1 Sol max 1,482
  26. 26 Claude Opus 4.8 high 1,482
  27. 27 GPT-5.5 high 1,481
  28. 28 MiMo-V2.6 Pro 1,480
  29. 29 Gemini 3.5 Flash high 1,478
  30. 30 GPT-5.2 Instant 1,476
  31. 31 GPT-5.4 high 1,475
  32. 32 GLM-5.2 max 1,475
  33. 33 DeepSeek V4.1 Flash max 1,475
  34. 34 GLM-5.3-Flash 1,474
  35. 35 GPT-6 Astra max 1,474
  36. 36 Qwen3.7-Max 1,474
  37. 37 Claude Opus 4.5 high, 32k 1,474
  38. 38 GPT-5.5 Instant 1,473
  39. 39 Gemini 3 Flash 1,473
  40. 40 Claude Sonnet 5.5 xhigh 1,472
  41. 41 Claude Sonnet 4.6 1,472
  42. 42 GPT-5.6 Terra xhigh 1,468
  43. 43 ERNIE 5.1 1,467
  44. 44 MiMo-V2.5-Pro 1,467
  45. 45 Grok 4.5 1,466
  46. 46 GLM-5.1 1,465
  47. 47 DeepSeek-V4-Pro high 1,464
  48. 48 Claude Sonnet 5 high 1,461
  49. 49 Kimi K2.6 1,461
  50. 50 Qwen 3.6 Max (Preview) 1,460
  51. 51 GLM-5 1,457
  52. 52 GPT-6 Sol max 1,457
  53. 53 Seed2.0 Pro 1,457
  54. 54 Grok 4.6 high 1,456
  55. 55 Claude Sonnet 4.5 high, 32k 1,456
  56. 56 GPT-5.1 high 1,455
  57. 57 Qwen3.7-Plus 1,455
  58. 58 Gemini 3.5 Flash-Lite 1,455
  59. 59 Tencent Hy3 1,454
  60. 60 GPT-5.6 Luna xhigh 1,453
  61. 61 Gemma 4 31B IT 1,452
  62. 62 GPT-5.3 Instant 1,450
  63. 63 Claude Opus 4.1 thinking 16k 1,450
  64. 64 Kimi K2.5 thinking 1,450
  65. 65 Step 5 Preview 1,448
  66. 66 MiMo-V2-Pro 1,448
  67. 67 MiMo-V2.6 Flash 1,448
  68. 68 GPT-5.4 Mini high 1,447
  69. 69 Gemini 2.5 Pro Jun 2025 1,446
  70. 70 GPT-4.5 1,445
  71. 71 Inkling 1,443
  72. 72 Qwen 3.6 Plus 1,443
  73. 73 GPT-4o Mar 2025 1,443
  74. 74 Grok 4.7 xhigh 1,442
  75. 75 Grok 4.3 1,442
  76. 76 Qwen3.5 397B-A17B 1,441
  77. 77 GLM-4.7 1,441
  78. 78 GPT-6 Luna max 1,441
  79. 79 DeepSeek-V4-Flash high 1,439
  80. 80 Gemma 4 26B A4B 1,438
  81. 81 GPT-5.2 high 1,437
  82. 82 MiniMax-M3 1,436
  83. 83 GPT-5 high 1,435
  84. 84 Beam 1.0 1,435
  85. 85 Qwen3-Max 1,434
  86. 86 GLM-5V-Turbo 1,434
  87. 87 MiMo-V2.5 1,434
  88. 88 Qwen 3.8 27B 1,433
  89. 89 Gemini 3.1 Flash-Lite 1,433
  90. 90 o3 1,432
  91. 91 Grok 4.1 Fast reasoning 1,431
  92. 92 MiMo-V2-Omni 1,430
  93. 93 GPT-5 Chat 1,427
  94. 94 Mistral Medium 3.5 1,427
  95. 95 Nemotron 3 Ultra nvfp4 1,426
  96. 96 Claude Opus 4 thinking 16k 1,426
  97. 97 DeepSeek-V3.2-Exp thinking 1,425
  98. 98 DeepSeek-V3.2 1,425
  99. 99 Muse Glimmer 1,425
  100. 100 GLM-4.6 1,424
  101. 101 Mistral Large 4 1,423
  102. 102 Claude Haiku 5.5 high 1,422
  103. 103 Qwen3-235B-A22B-Instruct Jul 2025 1,422
  104. 104 DeepSeek-R1 May 2025 1,421
  105. 105 Nemotron 3.5 Super VL 1,420
  106. 106 Grok 4 Fast non-reasoning 1,418
  107. 107 Kimi K2 Sep 2025 1,418
  108. 108 Mistral Large 3 1,418
  109. 109 Kimi K2 Jul 2025 1,418
  110. 110 DeepSeek-V3.1 1,417
  111. 111 Qwen3.5-122B-A10B 1,416
  112. 112 DeepSeek-V3.1-Terminus thinking 1,416
  113. 113 MiniMax-M2.7 1,415
  114. 114 GPT-4.1 1,415
  115. 115 Claude Haiku 4.5 1,414
  116. 116 Qwen3-VL-235B-A22B-Instruct 1,413
  117. 117 Inkling 2 Small 1,412
  118. 118 Grok 3 1,411
  119. 119 GLM-4.5 1,411
  120. 120 Grok 4 1,411
  121. 121 Gemini 2.5 Flash Jun 2025 1,409
  122. 122 Tencent Hy3 preview 1,409
  123. 123 Qwen3.5-27B 1,409
  124. 124 Mistral Medium 3.1 1,408
  125. 125 Inkling-Small 1,405
  126. 126 Gemini 2.5 Flash Sep 2025 1,403
  127. 127 o1 1,402
  128. 128 Qwen3-235B-A22B non-thinking 1,402
  129. 129 Claude Sonnet 4 thinking 32k 1,402
  130. 130 GPT-5.4 Nano high 1,401
  131. 131 LongCat-Flash-Chat 1,400
  132. 132 Qwen3-235B-A22B-Thinking Jul 2025 1,400
  133. 133 Qwen3-Next-80B-A3B-Instruct 1,399
  134. 134 DeepSeek-R1 1,398
  135. 135 Qwen3.5-Flash 1,396
  136. 136 DeepSeek-V3 Mar 2025 1,395
  137. 137 Qwen3-VL-235B-A22B thinking 1,395
  138. 138 Qwen3.5-35B-A3B 1,394
  139. 139 Step 3.5 Flash 1,393
  140. 140 MiMo-V2-Flash non-thinking 1,392
  141. 141 o4-mini 1,391
  142. 142 MiniMax-M2.5 1,391
  143. 143 GPT-5 mini high 1,390
  144. 144 o1-preview 1,389
  145. 145 Claude 3.7 Sonnet thinking 32k 1,388
  146. 146 Qwen3-Coder-480B-A35B 1,388
  147. 147 Solar Pro 4 1,387
  148. 148 Hunyuan-T1 1,387
  149. 149 Mistral Medium 3 1,387
  150. 150 MiniMax-M2.1 1,384
  151. 151 Hunyuan-TurboS 1,383
  152. 152 GPT-4.1 mini 1,383
  153. 153 Qwen3-30B-A3B-Instruct Jul 2025 1,382
  154. 154 Gemini 2.5 Flash-Lite Sep 2025, non-thinking, 09-2025 1,379
  155. 155 Trinity Large Preview 1,379
  156. 156 GLM-4.6V 1,378
  157. 157 Gemini 2.5 Flash-Lite Jun 2025 1,375
  158. 158 Claude 3.5 Sonnet (October 2024) 1,374
  159. 159 Qwen2.5-Max 1,374
  160. 160 GLM-4.5-Air 1,373
  161. 161 Qwen3-Next-80B-A3B thinking 1,369
  162. 162 Trinity Large Thinking 1,367
  163. 163 Gemma 3 27B 1,365
  164. 164 glm-4.7-flash 1,364
  165. 165 MiniMax-M1-80k 1,364
  166. 166 Grok-3 mini high 1,364
  167. 167 o3-mini high 1,364
  168. 168 Gemini 2.0 Flash Feb 2025 1,360
  169. 169 Nemotron 3 Super 1,360
  170. 170 DeepSeek-V3 1,358
  171. 171 Mistral Small 3.2 1,356
  172. 172 INTELLECT-3 1,356
  173. 173 Cohere Command A 1,354
  174. 174 Gemini 2.0 Flash-Lite 1,354
  175. 175 GLM-4.5V 1,352
  176. 176 gpt-oss-120b 1,352
  177. 177 Nemotron 3.5 Lightning 30B-A3B nvfp4 1,351
  178. 178 Gemini 1.5 Pro Sep 2024 1,351
  179. 179 Step 3 1,349
  180. 180 Llama-3.1-Nemotron-Ultra-253B-v1 1,348
  181. 181 Qwen3-32B 1,347
  182. 182 GPT-4o May 2024 1,346
  183. 183 MiniMax-M2 1,344
  184. 184 Claude 3.5 Sonnet 1,343
  185. 185 Llama-3.3-Nemotron-Super-49B-v1.5 1,343
  186. 186 Ling-flash-2.0 1,343
  187. 187 Mercury 2 1,343
  188. 188 Gemma 3 12B 1,342
  189. 189 Granite 4.2 30B 1,340
  190. 190 GPT-5 nano high 1,338
  191. 191 o1-mini 1,337
  192. 192 Grok-2 Aug 2024 1,336
  193. 193 GPT-4o Aug 2024 1,336
  194. 194 QwQ-32B 1,336
  195. 195 Llama 3.1-405B bf16 1,335
  196. 196 Nova 2 Lite 1,335
  197. 197 Olmo 3.1 32B Instruct 1,329
  198. 198 Yi-Lightning 1,328
  199. 199 Llama-3.3-Nemotron-Super-49B-v1 1,328
  200. 200 Llama 4 Maverick 1,327
  201. 201 Qwen3-30B-A3B 1,326
  202. 202 Claude 3.5 Haiku 1,325
  203. 203 GPT-4 Turbo Apr 2024 1,325
  204. 204 Gemini 1.5 Pro May 2024 1,324
  205. 205 DeepSeek-V2.5-1210 1,323
  206. 206 Ring-flash-2.0 1,322
  207. 207 GPT-4.1 nano 1,322
  208. 208 Claude 3 Opus 1,322
  209. 209 Llama 4 Scout 1,322
  210. 210 Molmo2-8B 1,321
  211. 211 Llama 3.3 70B Instruct 1,318
  212. 212 GPT-4o mini 1,318
  213. 213 gpt-oss-20b 1,318
  214. 214 Gemma 3n E4B 1,317
  215. 215 Mistral Large 2 Jul 2024 1,314
  216. 216 Athene-V2-Chat 1,314
  217. 217 Nemotron 3 Nano 30B-A3B bf16 1,314
  218. 218 GPT-4 Turbo (Jan 2024) 1,313
  219. 219 GPT-4 Turbo Nov 2023 1,313
  220. 220 Gemini 1.5 Flash Sep 2024 1,309
  221. 221 Grok-2 mini 1,308
  222. 222 DeepSeek-V2.5 Sep 2024 1,307
  223. 223 Athene-70B 1,307
  224. 224 Olmo 3 32B Think 1,306
  225. 225 Mistral Large 2 Nov 2024 1,306
  226. 226 Mercury 1,305
  227. 227 Magistral Medium 1.0 1,305
  228. 228 Granite 4.1 8B 1,304
  229. 229 Gemma 3 4B 1,303
  230. 230 Qwen2.5-72B 1,303
  231. 231 Mistral Small 3.1 1,303
  232. 232 Llama-3.1-Nemotron-70B-Instruct 1,299
  233. 233 Llama 3.1-70B 1,293
  234. 234 Amazon Nova Pro 1,290
  235. 235 Gemma 2 27B 1,290
  236. 236 Granite 4.2 8B 1,290
  237. 237 Jamba 1.5 Large 1,290
  238. 238 Granite 4.2 3B 1,289
  239. 239 Reka Core 1,288
  240. 240 GPT-4 Mar 2023 1,288
  241. 241 Granite 4.0 H Small 1,287
  242. 242 Llama-3.1-Nemotron-51B-Instruct 1,287
  243. 243 Gemini 1.5 Flash May 2024 1,287
  244. 244 Tulu 3 (Tülu 3) 70B 1,286
  245. 245 Olmo 3.1 32B Think 1,286
  246. 246 Claude 3 Sonnet 1,281
  247. 247 Nemotron-4-340B-Instruct 1,277
  248. 248 Llama 3-70B 1,277
  249. 249 GPT-4 Jun 2023 1,276
  250. 250 Command R+ 1,276
  251. 251 Mistral Small 3 1,274
  252. 252 Reka Flash 1,273
  253. 253 Qwen2.5-Coder-32B-Instruct 1,271
  254. 254 Aya Expanse 32B 1,267
  255. 255 Gemma 2 9B 1,267
  256. 256 DeepSeek-Coder-V2 236B 1,266
  257. 257 Qwen2-72B 1,262
  258. 258 Claude 3 Haiku 1,262
  259. 259 Amazon Nova Lite 1,260
  260. 260 Gemini 1.5 Flash 8B 1,259
  261. 261 Phi-4 1,256
  262. 262 OLMo 2 32B Instruct 1,252
  263. 263 c4ai-command-r-08-2024 1,251
  264. 264 Mistral Large 1,243
  265. 265 Amazon Nova Micro 1,241
  266. 266 Jamba 1.5 Mini 1,240
  267. 267 Ministral 8B 1,238
  268. 268 Gemini 1.0 Pro 1,237
  269. 269 Qwen1.5-110B 1,234
  270. 270 Qwen1.5-72B 1,234
  271. 271 Mixtral 8x22B 1,230
  272. 272 Command R (03-2024) 1,227
  273. 273 GPT-3.5 Turbo Jan 2024 1,226
  274. 274 Llama 3-8B 1,224
  275. 275 Aya Expanse 8B 1,223
  276. 276 Mistral Medium 1,223
  277. 277 Llama-3.1-Tulu-3-8B 1,221
  278. 278 Zephyr ORPO 141B A35B v0.1 1,213
  279. 279 Yi-1.5-34B 1,213
  280. 280 Llama 3.1-8B 1,211
  281. 281 Granite-3.1-8B-Instruct 1,209
  282. 282 GPT-3.5 Turbo Nov 2023 1,204
  283. 283 Qwen1.5-32B 1,204
  284. 284 Gemma 2 2B IT 1,200
  285. 285 phi-3-medium 14B 1,198
  286. 286 Mixtral 8x7B 1,197
  287. 287 DBRX 1,196
  288. 288 Qwen1.5-14B 1,191
  289. 289 InternLM2.5-20B-Chat 1,191
  290. 290 DeepSeek LLM 67B 1,185
  291. 291 Yi-34B 1,184
  292. 292 Granite-3.0-8B-Instruct 1,183
  293. 293 Gemma 1.1 7B IT 1,183
  294. 294 Snowflake Arctic Instruct 1,180
  295. 295 Granite-3.1-2B-Instruct 1,179
  296. 296 Tulu 2 DPO 70B 1,178
  297. 297 phi-3-small 7.4B 1,171
  298. 298 Starling-LM-7B-beta 1,171
  299. 299 Llama 2-70B 1,171
  300. 300 Starling-LM-7B-alpha 1,168
  301. 301 Llama 3.2 3B 1,167
  302. 302 Nous-Hermes-2-Mixtral-8x7B-DPO 1,164
  303. 303 Granite-3.0-2B-Instruct 1,157
  304. 304 Llama2-70B-SteerLM-Chat 1,155
  305. 305 QwQ-32B-Preview 1,154
  306. 306 SOLAR-10.7B-Instruct-v1.0 1,153
  307. 307 MPT-30B 1,151
  308. 308 Mistral 7B v0.2 1,149
  309. 309 Falcon-180B 1,148
  310. 310 Qwen1.5-7B 1,144
  311. 311 Llama 2-13B 1,142
  312. 312 Qwen-14B 1,140
  313. 313 Gemma 7B 1,138
  314. 314 Code Llama 34B Instruct 1,137
  315. 315 Zephyr 7B Beta 1,131
  316. 316 Phi-3-mini-128k-instruct 1,130
  317. 317 phi-3-mini 3.8B 1,128
  318. 318 Zephyr 7B Alpha 1,127
  319. 319 Code Llama 70B Instruct 1,119
  320. 320 Gemma 1.1 2B IT 1,117
  321. 321 SmolLM2 1.7B Instruct 1,115
  322. 322 Llama 3.2 1B 1,111
  323. 323 Mistral-7B-Instruct-v0.1 1,111
  324. 324 Llama 2-7B 1,108
  325. 325 Gemma 2B 1,094
  326. 326 Qwen1.5-4B-Chat 1,091
  327. 327 OLMo-7B-Instruct 1,074
  328. 328 MPT-7B 1,064
  329. 329 ChatGLM3-6B 1,057
  330. 330 Mistral 7B v0.1 1,031
  331. 331 chatglm2-6b 1,025
  332. 332 ChatGLM-6B 996
  333. 333 FastChat-T5-3B 993
  334. 334 Dolly 2.0-12b 983
  335. 335 LLaMA-13B 975
  336. 336 stablelm-tuned-alpha-7b 953

Sources: Official LMArena (Elo) leaderboard and labs’ model cards

#EntryScoreSettingDateSource
1 Gemini 4 Carbon 1,526 high Oct 2026 Official leaderboard
2 Gemini 4 Argon 1,522 high Sep 2026 Official leaderboard
3 Muse Wonder 1,511 max Oct 2026 Official leaderboard
4 Claude Opus 5.5 1,506 high Sep 2026 Official leaderboard
5 Claude Fable 5 1,504 high Jun 2026 Official leaderboard
6 Claude Opus 4.6 1,503 high Feb 2026 Official leaderboard
7 Claude Fable 5.1 1,503 max Sep 2026 Official leaderboard
8 Claude Opus 4.7 1,501 high Apr 2026 Official leaderboard
9 Gemini 3.8 Flash 1,497 high Sep 2026 Official leaderboard
10 Muse Spark 1.3 1,496 max Sep 2026 Official leaderboard
11 Muse Spark 1.2 1,493 xhigh Aug 2026 Official leaderboard
12 Muse Spark 1.1 1,491 Jul 2026 Official leaderboard
13 Claude Opus 5 1,490 high Jul 2026 Official leaderboard
14 Gemini 3.7 Flash 1,489 high Aug 2026 Official leaderboard
15 Muse Spark 1,489 Apr 2026 Official leaderboard
16 Kimi K3 1,487 max Jul 2026 Official leaderboard
17 Gemini 3.1 Pro 1,487 Feb 2026 Official leaderboard
18 Gemini 3 Pro 1,486 Nov 2025 Official leaderboard
19 GPT-5.6 Sol 1,485 xhigh Jul 2026 Official leaderboard
20 Qwen 3.8 Max 1,484 Aug 2026 Official leaderboard
21 Kimi K3.1 Pro 1,483 max Oct 2026 Official leaderboard
22 Gemini 3.6 Flash 1,483 high Jul 2026 Official leaderboard
23 GLM-5.3 1,483 max Aug 2026 Official leaderboard
24 GPT-6.1 Sol 1,482 max Sep 2026 Official leaderboard
25 Claude Opus 4.8 1,482 high May 2026 Official leaderboard
26 GPT-5.5 1,481 high Apr 2026 Official leaderboard
27 MiMo-V2.6 Pro 1,480 Sep 2026 Official leaderboard
28 Gemini 3.5 Flash 1,478 high May 2026 Official leaderboard
29 GPT-5.2 Instant 1,476 Dec 2025 Official leaderboard
30 GPT-5.4 1,475 high Mar 2026 Official leaderboard
31 GLM-5.2 1,475 max Jun 2026 Official leaderboard
32 DeepSeek V4.1 Flash 1,475 max Sep 2026 Official leaderboard
33 Grok 4.20 Beta 1 1,475 Nov 2026 Official leaderboard
34 GLM-5.3-Flash 1,474 Aug 2026 Official leaderboard
35 GPT-6 Astra 1,474 max Sep 2026 Official leaderboard
36 Qwen3.7-Max 1,474 May 2026 Official leaderboard
37 Claude Opus 4.5 1,474 high, 32k Nov 2025 Official leaderboard
38 GPT-5.5 Instant 1,473 May 2026 Official leaderboard
39 Gemini 3 Flash 1,473 Dec 2025 Official leaderboard
40 Claude Sonnet 5.5 1,472 xhigh Sep 2026 Official leaderboard
41 Grok 4.20 Beta (Reasoning, 0309) 1,472 Nov 2026 Official leaderboard
42 Claude Sonnet 4.6 1,472 Feb 2026 Official leaderboard
43 Grok 4.20 Multi-Agent Beta (0309) 1,471 Nov 2026 Official leaderboard
44 GPT-5.6 Terra 1,468 xhigh Jul 2026 Official leaderboard
45 ERNIE 5.1 1,467 May 2026 Official leaderboard
46 MiMo-V2.5-Pro 1,467 Apr 2026 Official leaderboard
47 Grok 4.5 1,466 Jul 2026 Official leaderboard
48 Grok 4.1 1,465 thinking Nov 2025 Official leaderboard
49 GLM-5.1 1,465 Apr 2026 Official leaderboard
50 Qwen3.5-Max-Preview 1,465 Nov 2026 Official leaderboard
51 DeepSeek-V4-Pro 1,464 high Apr 2026 Official leaderboard
52 Claude Sonnet 5 1,461 high Jun 2026 Official leaderboard
53 Kimi K2.6 1,461 Apr 2026 Official leaderboard
54 Qwen 3.6 Max (Preview) 1,460 Apr 2026 Official leaderboard
55 GLM-5 1,457 Feb 2026 Official leaderboard
56 GPT-6 Sol 1,457 max Sep 2026 Official leaderboard
57 Seed2.0 Pro 1,457 Feb 2026 Official leaderboard
58 Grok 4.6 1,456 high Aug 2026 Official leaderboard
59 Claude Sonnet 4.5 1,456 high, 32k Sep 2025 Official leaderboard
60 GPT-5.1 1,455 high Nov 2025 Official leaderboard
61 Qwen3.7-Plus 1,455 Jun 2026 Official leaderboard
62 Gemini 3.5 Flash-Lite 1,455 Jul 2026 Official leaderboard
63 Tencent Hy3 1,454 Jul 2026 Official leaderboard
64 GPT-5.6 Luna 1,453 xhigh Jul 2026 Official leaderboard
65 Gemma 4 31B IT 1,452 Apr 2026 Official leaderboard
66 GPT-5.3 Instant 1,450 Mar 2026 Official leaderboard
67 Claude Opus 4.1 1,450 thinking 16k Aug 2025 Official leaderboard
68 Kimi K2.5 1,450 thinking Jan 2026 Official leaderboard
69 ERNIE-5.0-Preview (1203) 1,449 Nov 2026 Official leaderboard
70 Step 5 Preview 1,448 Sep 2026 Official leaderboard
71 MiMo-V2-Pro 1,448 Mar 2026 Official leaderboard
72 MiMo-V2.6 Flash 1,448 Sep 2026 Official leaderboard
73 GPT-5.4 Mini 1,447 high Mar 2026 Official leaderboard
74 ERNIE 5.0 (0110) 1,446 Nov 2026 Official leaderboard
75 Gemini 2.5 Pro Jun 2025 1,446 Jun 2025 Official leaderboard
76 GPT-4.5 1,445 Feb 2025 Official leaderboard
77 Inkling 1,443 Jul 2026 Official leaderboard
78 Qwen 3.6 Plus 1,443 Mar 2026 Official leaderboard
79 GPT-4o Mar 2025 1,443 Mar 2025 Official leaderboard
80 Grok 4.7 1,442 xhigh Sep 2026 Official leaderboard
81 Grok 4.3 1,442 Apr 2026 Official leaderboard
82 Qwen3.5 397B-A17B 1,441 Feb 2026 Official leaderboard
83 GLM-4.7 1,441 Dec 2025 Official leaderboard
84 GPT-6 Luna 1,441 max Sep 2026 Official leaderboard
85 DeepSeek-V4-Flash 1,439 high Apr 2026 Official leaderboard
86 Gemma 4 26B A4B 1,437 Apr 2026 Official leaderboard
87 GPT-5.2 1,437 high Dec 2025 Official leaderboard
88 LongCat-Flash-Chat Exp (2602) 1,436 Nov 2026 Official leaderboard
89 MiniMax-M3 1,436 Jun 2026 Official leaderboard
90 GPT-5 1,435 high Aug 2025 Official leaderboard
91 Beam 1.0 1,435 Oct 2026 Official leaderboard
92 Qwen3-Max 1,434 Sep 2025 Official leaderboard
93 GLM-5V-Turbo 1,434 Apr 2026 Official leaderboard
94 MiMo-V2.5 1,434 Apr 2026 Official leaderboard
95 Qwen 3.8 27B 1,433 Aug 2026 Official leaderboard
96 Gemini 3.1 Flash-Lite 1,433 Mar 2026 Official leaderboard
97 o3 1,432 Apr 2025 Official leaderboard
98 Grok 4.1 Fast 1,431 reasoning Nov 2025 Official leaderboard
99 MiMo-V2-Omni 1,430 Mar 2026 Official leaderboard
100 Kimi K2 Thinking Turbo 1,430 Nov 2026 Official leaderboard
101 GPT-5 Chat 1,427 Aug 2025 Official leaderboard
102 amazon-nova-experimental-chat (26-02-10) 1,427 Nov 2026 Official leaderboard
103 Mistral Medium 3.5 1,427 Apr 2026 Official leaderboard
104 Nemotron 3 Ultra 1,426 nvfp4 Jun 2026 Official leaderboard
105 Claude Opus 4 1,426 thinking 16k May 2025 Official leaderboard
106 DeepSeek-V3.2-Exp 1,425 thinking Sep 2025 Official leaderboard
107 DeepSeek-V3.2 1,425 Dec 2025 Official leaderboard
108 Muse Glimmer 1,425 Aug 2026 Official leaderboard
109 GLM-4.6 1,424 Sep 2025 Official leaderboard
110 Mistral Large 4 1,423 Oct 2026 Official leaderboard
111 Claude Haiku 5.5 1,422 high Oct 2026 Official leaderboard
112 Qwen3-235B-A22B-Instruct Jul 2025 1,422 Jul 2025 Official leaderboard
113 DeepSeek-R1 May 2025 1,421 May 2025 Official leaderboard
114 Grok 4 Fast 1,418 non-reasoning Sep 2025 Official leaderboard
115 Kimi K2 Sep 2025 1,418 Sep 2025 Official leaderboard
116 ERNIE-5.0-Preview (1022) 1,418 Nov 2026 Official leaderboard
117 Kimi K2 Jul 2025 1,418 Jul 2025 Official leaderboard
118 DeepSeek-V3.1 1,417 Aug 2025 Official leaderboard
119 Qwen3.5-122B-A10B 1,416 Feb 2026 Official leaderboard
120 DeepSeek-V3.1-Terminus 1,416 thinking Sep 2025 Official leaderboard
121 Nemotron 3.5 Super VL 1,415 nvfp4 Oct 2026 Official leaderboard
122 MiniMax-M2.7 1,415 Mar 2026 Official leaderboard
123 Mistral Large 3 1,415 Dec 2025 Official leaderboard
124 GPT-4.1 1,415 Apr 2025 Official leaderboard
125 Claude Haiku 4.5 1,414 Oct 2025 Official leaderboard
126 Qwen3-VL-235B-A22B-Instruct 1,413 Sep 2025 Official leaderboard
127 Inkling 2 Small 1,412 Nov 2026 Official leaderboard
128 amazon-nova-experimental-chat (26-01-10) 1,412 Nov 2026 Official leaderboard
129 Grok 3 1,411 Apr 2025 Official leaderboard
130 GLM-4.5 1,411 Aug 2025 Official leaderboard
131 Grok 4 1,411 Jul 2025 Official leaderboard
132 Gemini 2.5 Flash Jun 2025 1,409 Jun 2025 Official leaderboard
133 Tencent Hy3 preview 1,409 Apr 2026 Official leaderboard
134 Qwen3.5-27B 1,409 Feb 2026 Official leaderboard
135 Mistral Medium 3.1 1,408 Aug 2025 Official leaderboard
136 Inkling-Small 1,405 Jul 2026 Official leaderboard
137 Gemini 2.5 Flash Sep 2025 1,403 Sep 2025 Official leaderboard
138 o1 1,402 Dec 2024 Official leaderboard
139 Qwen3-235B-A22B 1,402 non-thinking Apr 2025 Official leaderboard
140 Claude Sonnet 4 1,402 thinking 32k May 2025 Official leaderboard
141 GPT-5.4 Nano 1,401 high Mar 2026 Official leaderboard
142 LongCat-Flash-Chat 1,400 Aug 2025 Official leaderboard
143 Qwen3-235B-A22B-Thinking Jul 2025 1,400 Jul 2025 Official leaderboard
144 Qwen3-Next-80B-A3B-Instruct 1,399 Sep 2025 Official leaderboard
145 DeepSeek-R1 1,398 Jan 2025 Official leaderboard
146 Qwen3.5-Flash 1,396 Feb 2026 Official leaderboard
147 DeepSeek-V3 Mar 2025 1,395 Mar 2025 Official leaderboard
148 Qwen3-VL-235B-A22B 1,395 thinking Sep 2025 Official leaderboard
149 Hunyuan Vision 1.5 Thinking 1,394 Nov 2026 Official leaderboard
150 Qwen3.5-35B-A3B 1,394 Feb 2026 Official leaderboard
151 Step 3.5 Flash 1,393 Feb 2026 Official leaderboard
152 amazon-nova-experimental-chat (12-10) 1,393 Nov 2026 Official leaderboard
153 MiMo-V2-Flash 1,392 non-thinking Dec 2025 Official leaderboard
154 o4-mini 1,391 Apr 2025 Official leaderboard
155 MiniMax-M2.5 1,391 Feb 2026 Official leaderboard
156 GPT-5 mini 1,390 high Aug 2025 Official leaderboard
157 o1-preview 1,389 Sep 2024 Official leaderboard
158 Claude 3.7 Sonnet 1,388 thinking 32k Feb 2025 Official leaderboard
159 Qwen3-Coder-480B-A35B 1,388 Jul 2025 Official leaderboard
160 Solar Pro 4 1,387 Aug 2026 Official leaderboard
161 Hunyuan-T1 1,387 Mar 2025 Official leaderboard
162 Mistral Medium 3 1,387 May 2025 Official leaderboard
163 MiniMax-M2.1 1,384 Dec 2025 Official leaderboard
164 Hunyuan-TurboS 1,383 Feb 2025 Official leaderboard
165 GPT-4.1 mini 1,383 Apr 2025 Official leaderboard
166 Qwen3-30B-A3B-Instruct Jul 2025 1,382 Jul 2025 Official leaderboard
167 Gemini 2.5 Flash-Lite Sep 2025 1,379 non-thinking, 09-2025 Sep 2025 Official leaderboard
168 Trinity Large Preview 1,379 Jan 2026 Official leaderboard
169 GLM-4.6V 1,378 Dec 2025 Official leaderboard
170 Gemini 2.5 Flash-Lite Jun 2025 1,375 Jun 2025 Official leaderboard
171 Claude 3.5 Sonnet (October 2024) 1,374 Oct 2024 Official leaderboard
172 Qwen2.5-Max 1,374 Jan 2025 Official leaderboard
173 GLM-4.5-Air 1,373 Jul 2025 Official leaderboard
174 Qwen3-Next-80B-A3B 1,369 thinking Sep 2025 Official leaderboard
175 Trinity Large Thinking 1,367 Apr 2026 Official leaderboard
176 Gemma 3 27B 1,365 Mar 2025 Official leaderboard
177 glm-4.7-flash 1,364 Jan 2026 Official leaderboard
178 MiniMax-M1-80k 1,364 Jun 2025 Official leaderboard
179 Grok-3 mini 1,364 high Apr 2025 Official leaderboard
180 o3-mini 1,364 high Jan 2025 Official leaderboard
181 amazon-nova-experimental-chat (11-10) 1,363 Nov 2026 Official leaderboard
182 Gemini 2.0 Flash Feb 2025 1,360 Feb 2025 Official leaderboard
183 Nemotron 3 Super 1,360 Mar 2026 Official leaderboard
184 DeepSeek-V3 1,358 Dec 2024 Official leaderboard
185 Mistral Small 3.2 1,356 Jun 2025 Official leaderboard
186 INTELLECT-3 1,356 Nov 2025 Official leaderboard
187 Cohere Command A 1,354 Mar 2025 Official leaderboard
188 Gemini 2.0 Flash-Lite 1,354 Feb 2025 Official leaderboard
189 GLM-4.5V 1,352 Aug 2025 Official leaderboard
190 gpt-oss-120b 1,352 Aug 2025 Official leaderboard
191 Nemotron 3.5 Lightning 30B-A3B 1,351 nvfp4 Aug 2026 Official leaderboard
192 Gemini 1.5 Pro Sep 2024 1,351 Sep 2024 Official leaderboard
193 Step 3 1,349 Jul 2025 Official leaderboard
194 amazon-nova-experimental-chat (10-20) 1,348 Nov 2026 Official leaderboard
195 Llama-3.1-Nemotron-Ultra-253B-v1 1,348 Apr 2025 Official leaderboard
196 Qwen3-32B 1,347 Apr 2025 Official leaderboard
197 GPT-4o May 2024 1,346 May 2024 Official leaderboard
198 amazon-nova-experimental-chat (10-09) 1,346 Nov 2026 Official leaderboard
199 Qwen-Plus (0125) 1,346 Nov 2026 Official leaderboard
200 MiniMax-M2 1,344 Oct 2025 Official leaderboard
201 Claude 3.5 Sonnet 1,343 Jun 2024 Official leaderboard
202 Llama-3.3-Nemotron-Super-49B-v1.5 1,343 Jul 2025 Official leaderboard
203 Ling-flash-2.0 1,343 Sep 2025 Official leaderboard
204 Mercury 2 1,343 Feb 2026 Official leaderboard
205 GLM-4-Plus (0111) 1,343 Nov 2026 Official leaderboard
206 Gemma 3 12B 1,342 Mar 2025 Official leaderboard
207 Hunyuan Turbo (0110) 1,341 Nov 2026 Official leaderboard
208 Granite 4.2 30B 1,340 Aug 2026 Official leaderboard
209 GPT-5 nano 1,338 high Aug 2025 Official leaderboard
210 o1-mini 1,337 Sep 2024 Official leaderboard
211 Gemini Advanced (0514) 1,336 Nov 2026 Official leaderboard
212 Grok-2 Aug 2024 1,336 Aug 2024 Official leaderboard
213 GPT-4o Aug 2024 1,336 Aug 2024 Official leaderboard
214 QwQ-32B 1,336 Mar 2025 Official leaderboard
215 Llama 3.1-405B 1,335 bf16 Jul 2024 Official leaderboard
216 Nova 2 Lite 1,335 Dec 2025 Official leaderboard
217 Step-2 16K Exp (202412) 1,334 Nov 2026 Official leaderboard
218 Olmo 3.1 32B Instruct 1,329 Dec 2025 Official leaderboard
219 Yi-Lightning 1,328 Dec 2024 Official leaderboard
220 Llama-3.3-Nemotron-Super-49B-v1 1,328 Mar 2025 Official leaderboard
221 Llama 4 Maverick 1,327 Apr 2025 Official leaderboard
222 Qwen3-30B-A3B 1,326 Apr 2025 Official leaderboard
223 Hunyuan Large 20250210 1,326 Feb 2025 Official leaderboard
224 Claude 3.5 Haiku 1,325 Oct 2024 Official leaderboard
225 GPT-4 Turbo Apr 2024 1,325 Apr 2024 Official leaderboard
226 Gemini 1.5 Pro May 2024 1,324 May 2024 Official leaderboard
227 DeepSeek-V2.5-1210 1,323 Dec 2024 Official leaderboard
228 Ring-flash-2.0 1,322 Sep 2025 Official leaderboard
229 GPT-4.1 nano 1,322 Apr 2025 Official leaderboard
230 Claude 3 Opus 1,322 Feb 2024 Official leaderboard
231 Llama 4 Scout 1,322 Apr 2025 Official leaderboard
232 Molmo2-8B 1,321 Dec 2025 Official leaderboard
233 Step-1o Turbo (202506) 1,320 Nov 2026 Official leaderboard
234 GLM-4-Plus 1,319 Nov 2026 Official leaderboard
235 Qwen-Max (0919) 1,318 Nov 2026 Official leaderboard
236 Llama 3.3 70B Instruct 1,318 Dec 2024 Official leaderboard
237 GPT-4o mini 1,318 Jul 2024 Official leaderboard
238 gpt-oss-20b 1,318 Aug 2025 Official leaderboard
239 Gemma 3n E4B 1,317 Jun 2025 Official leaderboard
240 Qwen2.5-Plus (1127) 1,315 Nov 2026 Official leaderboard
241 Mistral Large 2 Jul 2024 1,314 Jul 2024 Official leaderboard
242 Athene-V2-Chat 1,314 Nov 2024 Official leaderboard
243 Nemotron 3 Nano 30B-A3B 1,314 bf16 Dec 2025 Official leaderboard
244 GPT-4 Turbo (Jan 2024) 1,313 Jan 2024 Official leaderboard
245 GPT-4 Turbo Nov 2023 1,313 Nov 2023 Official leaderboard
246 Hunyuan Standard 20250210 1,311 Feb 2025 Official leaderboard
247 Gemini 1.5 Flash Sep 2024 1,309 Aug 2024 Official leaderboard
248 Grok-2 mini 1,308 Aug 2024 Official leaderboard
249 DeepSeek-V2.5 Sep 2024 1,307 Sep 2024 Official leaderboard
250 Athene-70B 1,307 Jul 2024 Official leaderboard
251 Olmo 3 32B Think 1,306 Nov 2025 Official leaderboard
252 Mistral Large 2 Nov 2024 1,306 Nov 2024 Official leaderboard
253 Mercury 1,305 Jun 2025 Official leaderboard
254 Magistral Medium 1.0 1,305 Jun 2025 Official leaderboard
255 Granite 4.1 8B 1,304 Apr 2026 Official leaderboard
256 Gemma 3 4B 1,303 Mar 2025 Official leaderboard
257 Qwen2.5-72B 1,303 Sep 2024 Official leaderboard
258 Mistral Small 3.1 1,303 Mar 2025 Official leaderboard
259 Llama-3.1-Nemotron-70B-Instruct 1,299 Oct 2024 Official leaderboard
260 Hunyuan Large Vision 1,294 Nov 2026 Official leaderboard
261 Llama 3.1-70B 1,293 Jul 2024 Official leaderboard
262 Amazon Nova Pro 1,290 Dec 2024 Official leaderboard
263 Gemma 2 27B 1,290 Jun 2024 Official leaderboard
264 Granite 4.2 8B 1,290 Aug 2026 Official leaderboard
265 Jamba 1.5 Large 1,290 Aug 2024 Official leaderboard
266 Granite 4.2 3B 1,289 Aug 2026 Official leaderboard
267 Reka Core 1,288 Apr 2024 Official leaderboard
268 GPT-4 Mar 2023 1,288 Mar 2023 Official leaderboard
269 Granite 4.0 H Small 1,287 Oct 2025 Official leaderboard
270 Llama-3.1-Nemotron-51B-Instruct 1,287 Sep 2024 Official leaderboard
271 Gemini 1.5 Flash May 2024 1,287 May 2024 Official leaderboard
272 Tulu 3 (Tülu 3) 70B 1,286 Nov 2024 Official leaderboard
273 Olmo 3.1 32B Think 1,286 Dec 2025 Official leaderboard
274 Claude 3 Sonnet 1,281 Feb 2024 Official leaderboard
275 Gemma 2 9B IT SimPO 1,280 Nov 2026 Official leaderboard
276 Nemotron-4-340B-Instruct 1,277 Jun 2024 Official leaderboard
277 Llama 3-70B 1,277 Apr 2024 Official leaderboard
278 GPT-4 Jun 2023 1,276 Jun 2023 Official leaderboard
279 Command R+ 1,276 Aug 2024 Official leaderboard
280 Mistral Small 3 1,274 Jan 2025 Official leaderboard
281 GLM-4 (0520) 1,273 Nov 2026 Official leaderboard
282 Reka Flash 1,273 Feb 2024 Official leaderboard
283 Qwen2.5-Coder-32B-Instruct 1,271 Nov 2024 Official leaderboard
284 Aya Expanse 32B 1,267 Oct 2024 Official leaderboard
285 Gemma 2 9B 1,267 Jun 2024 Official leaderboard
286 DeepSeek-Coder-V2 236B 1,266 Jun 2024 Official leaderboard
287 Qwen2-72B 1,262 Jun 2024 Official leaderboard
288 Claude 3 Haiku 1,262 Mar 2024 Official leaderboard
289 Amazon Nova Lite 1,260 Dec 2024 Official leaderboard
290 Gemini 1.5 Flash 8B 1,259 Oct 2024 Official leaderboard
291 Phi-4 1,256 Dec 2024 Official leaderboard
292 OLMo 2 32B Instruct 1,252 Mar 2025 Official leaderboard
293 c4ai-command-r-08-2024 1,251 Aug 2024 Official leaderboard
294 Mistral Large 1,243 Feb 2024 Official leaderboard
295 Amazon Nova Micro 1,241 Dec 2024 Official leaderboard
296 Jamba 1.5 Mini 1,240 Aug 2024 Official leaderboard
297 Ministral 8B 1,238 Oct 2024 Official leaderboard
298 Gemini 1.0 Pro 1,237 Dec 2023 Official leaderboard
299 Qwen1.5-110B 1,234 Apr 2024 Official leaderboard
300 Qwen1.5-72B 1,234 Feb 2024 Official leaderboard
301 Reka Flash 21B (Online) 1,234 Feb 2024 Official leaderboard
302 Hunyuan Standard 256K 1,233 Nov 2026 Official leaderboard
303 Mixtral 8x22B 1,230 Apr 2024 Official leaderboard
304 Command R (03-2024) 1,227 Mar 2024 Official leaderboard
305 GPT-3.5 Turbo Jan 2024 1,226 Jan 2024 Official leaderboard
306 Llama 3-8B 1,224 Apr 2024 Official leaderboard
307 Aya Expanse 8B 1,223 Oct 2024 Official leaderboard
308 Mistral Medium 1,223 Dec 2023 Official leaderboard
309 Llama-3.1-Tulu-3-8B 1,221 Nov 2024 Official leaderboard
310 Zephyr ORPO 141B A35B v0.1 1,213 Apr 2024 Official leaderboard
311 Yi-1.5-34B 1,213 May 2024 Official leaderboard
312 Llama 3.1-8B 1,211 Jul 2024 Official leaderboard
313 Granite-3.1-8B-Instruct 1,209 Dec 2024 Official leaderboard
314 GPT-3.5 Turbo Nov 2023 1,204 Nov 2023 Official leaderboard
315 Qwen1.5-32B 1,204 Feb 2024 Official leaderboard
316 Gemma 2 2B IT 1,200 Jul 2024 Official leaderboard
317 phi-3-medium 14B 1,198 Apr 2024 Official leaderboard
318 Mixtral 8x7B 1,197 Dec 2023 Official leaderboard
319 DBRX 1,196 Mar 2024 Official leaderboard
320 Qwen1.5-14B 1,191 Feb 2024 Official leaderboard
321 InternLM2.5-20B-Chat 1,191 Aug 2024 Official leaderboard
322 DeepSeek LLM 67B 1,185 Nov 2023 Official leaderboard
323 WizardLM 70B 1,185 Nov 2026 Official leaderboard
324 Yi-34B 1,184 Nov 2023 Official leaderboard
325 Granite-3.0-8B-Instruct 1,183 Oct 2024 Official leaderboard
326 OpenChat 3.5 1,183 Nov 2026 Official leaderboard
327 OpenChat 3.5 (0106) 1,183 Nov 2026 Official leaderboard
328 Gemma 1.1 7B IT 1,183 Apr 2024 Official leaderboard
329 Snowflake Arctic Instruct 1,180 Apr 2024 Official leaderboard
330 Granite-3.1-2B-Instruct 1,179 Dec 2024 Official leaderboard
331 Tulu 2 DPO 70B 1,178 Nov 2023 Official leaderboard
332 OpenHermes 2.5 Mistral 7B 1,176 Nov 2026 Official leaderboard
333 Vicuna 33B 1,173 Nov 2026 Official leaderboard
334 phi-3-small 7.4B 1,171 Apr 2024 Official leaderboard
335 Starling-LM-7B-beta 1,171 Mar 2024 Official leaderboard
336 Llama 2-70B 1,171 Jul 2023 Official leaderboard
337 Starling-LM-7B-alpha 1,168 Nov 2023 Official leaderboard
338 Llama 3.2 3B 1,167 Sep 2024 Official leaderboard
339 Nous-Hermes-2-Mixtral-8x7B-DPO 1,164 Jan 2024 Official leaderboard
340 Granite-3.0-2B-Instruct 1,157 Oct 2024 Official leaderboard
341 Llama2-70B-SteerLM-Chat 1,155 Nov 2023 Official leaderboard
342 QwQ-32B-Preview 1,154 Nov 2024 Official leaderboard
343 SOLAR-10.7B-Instruct-v1.0 1,153 Dec 2023 Official leaderboard
344 Dolphin 2.2.1 Mistral 7B 1,152 Nov 2026 Official leaderboard
345 MPT-30B 1,151 Jun 2023 Official leaderboard
346 WizardLM 13B 1,150 Nov 2026 Official leaderboard
347 Mistral 7B v0.2 1,149 Dec 2023 Official leaderboard
348 Falcon-180B 1,148 Sep 2023 Official leaderboard
349 Qwen1.5-7B 1,144 Feb 2024 Official leaderboard
350 Phi-3 Mini 4K Instruct (June 2024) 1,143 Nov 2026 Official leaderboard
351 Vicuna 13B 1,142 Nov 2026 Official leaderboard
352 Llama 2-13B 1,142 Jul 2023 Official leaderboard
353 Qwen-14B 1,140 Sep 2023 Official leaderboard
354 PaLM 2 1,139 Nov 2026 Official leaderboard
355 Gemma 7B 1,138 Feb 2024 Official leaderboard
356 Code Llama 34B Instruct 1,137 Aug 2023 Official leaderboard
357 Zephyr 7B Beta 1,131 Oct 2023 Official leaderboard
358 Phi-3-mini-128k-instruct 1,130 Apr 2024 Official leaderboard
359 phi-3-mini 3.8B 1,128 Apr 2024 Official leaderboard
360 Guanaco 33B 1,128 Nov 2026 Official leaderboard
361 Zephyr 7B Alpha 1,127 Oct 2023 Official leaderboard
362 StripedHyena Nous 7B 1,122 Nov 2026 Official leaderboard
363 Code Llama 70B Instruct 1,119 Jan 2024 Official leaderboard
364 Gemma 1.1 2B IT 1,117 Apr 2024 Official leaderboard
365 Vicuna 7B 1,115 Nov 2026 Official leaderboard
366 SmolLM2 1.7B Instruct 1,115 Oct 2024 Official leaderboard
367 Llama 3.2 1B 1,111 Sep 2024 Official leaderboard
368 Mistral-7B-Instruct-v0.1 1,111 Sep 2023 Official leaderboard
369 Llama 2-7B 1,108 Jul 2023 Official leaderboard
370 Gemma 2B 1,094 Feb 2024 Official leaderboard
371 Qwen1.5-4B-Chat 1,091 Feb 2024 Official leaderboard
372 OLMo-7B-Instruct 1,074 Feb 2024 Official leaderboard
373 Koala 13B 1,071 Nov 2026 Official leaderboard
374 Alpaca 13B 1,070 Nov 2026 Official leaderboard
375 GPT4All 13B Snoozy 1,068 Nov 2026 Official leaderboard
376 MPT-7B 1,064 May 2023 Official leaderboard
377 ChatGLM3-6B 1,057 Oct 2023 Official leaderboard
378 RWKV-4 Raven 14B 1,042 Nov 2026 Official leaderboard
379 chatglm2-6b 1,025 Jun 2023 Official leaderboard
380 OpenAssistant Pythia 12B 1,024 Nov 2026 Official leaderboard
381 ChatGLM-6B 996 Mar 2023 Official leaderboard
382 FastChat-T5-3B 993 Apr 2023 Official leaderboard
383 Dolly 2.0-12b 983 Apr 2023 Official leaderboard
384 LLaMA-13B 975 Feb 2023 Official leaderboard
385 stablelm-tuned-alpha-7b 953 Apr 2023 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 4 Carbon 1,526 high Oct 2026 Official leaderboard
2 Gemini 4 Argon 1,522 high Sep 2026 Official leaderboard
3 Muse Wonder 1,511 max Oct 2026 Official leaderboard
4 Claude Opus 5.5 1,506 high Sep 2026 Official leaderboard
5 Claude Fable 5 1,504 high Jun 2026 Official leaderboard
6 Claude Opus 4.6 1,503 high Feb 2026 Official leaderboard
7 Claude Fable 5.1 1,503 max Sep 2026 Official leaderboard
8 Claude Opus 4.7 1,501 high Apr 2026 Official leaderboard
9 Gemini 3.8 Flash 1,497 high Sep 2026 Official leaderboard
10 Muse Spark 1.3 1,496 max Sep 2026 Official leaderboard
11 Muse Spark 1.2 1,493 xhigh Aug 2026 Official leaderboard
12 Muse Spark 1.1 1,491 Jul 2026 Official leaderboard
13 Claude Opus 5 1,490 high Jul 2026 Official leaderboard
14 Gemini 3.7 Flash 1,489 high Aug 2026 Official leaderboard
15 Muse Spark 1,489 Apr 2026 Official leaderboard
16 Kimi K3 1,487 max Jul 2026 Official leaderboard
17 Gemini 3.1 Pro 1,487 Feb 2026 Official leaderboard
18 Gemini 3 Pro 1,486 Nov 2025 Official leaderboard
19 GPT-5.6 Sol 1,485 xhigh Jul 2026 Official leaderboard
20 Qwen 3.8 Max 1,484 Aug 2026 Official leaderboard
21 Kimi K3.1 Pro 1,483 max Oct 2026 Official leaderboard
22 Grok 4.1 1,483 Nov 2025 Lab model card
23 Gemini 3.6 Flash 1,483 high Jul 2026 Official leaderboard
24 GLM-5.3 1,483 max Aug 2026 Official leaderboard
25 GPT-6.1 Sol 1,482 max Sep 2026 Official leaderboard
26 Claude Opus 4.8 1,482 high May 2026 Official leaderboard
27 GPT-5.5 1,481 high Apr 2026 Official leaderboard
28 MiMo-V2.6 Pro 1,480 Sep 2026 Official leaderboard
29 Gemini 3.5 Flash 1,478 high May 2026 Official leaderboard
30 GPT-5.2 Instant 1,476 Dec 2025 Official leaderboard
31 GPT-5.4 1,475 high Mar 2026 Official leaderboard
32 GLM-5.2 1,475 max Jun 2026 Official leaderboard
33 DeepSeek V4.1 Flash 1,475 max Sep 2026 Official leaderboard
34 GLM-5.3-Flash 1,474 Aug 2026 Official leaderboard
35 GPT-6 Astra 1,474 max Sep 2026 Official leaderboard
36 Qwen3.7-Max 1,474 May 2026 Official leaderboard
37 Claude Opus 4.5 1,474 high, 32k Nov 2025 Official leaderboard
38 GPT-5.5 Instant 1,473 May 2026 Official leaderboard
39 Gemini 3 Flash 1,473 Dec 2025 Official leaderboard
40 Claude Sonnet 5.5 1,472 xhigh Sep 2026 Official leaderboard
41 Claude Sonnet 4.6 1,472 Feb 2026 Official leaderboard
42 GPT-5.6 Terra 1,468 xhigh Jul 2026 Official leaderboard
43 ERNIE 5.1 1,467 May 2026 Official leaderboard
44 MiMo-V2.5-Pro 1,467 Apr 2026 Official leaderboard
45 Grok 4.5 1,466 Jul 2026 Official leaderboard
46 GLM-5.1 1,465 Apr 2026 Official leaderboard
47 DeepSeek-V4-Pro 1,464 high Apr 2026 Official leaderboard
48 Claude Sonnet 5 1,461 high Jun 2026 Official leaderboard
49 Kimi K2.6 1,461 Apr 2026 Official leaderboard
50 Qwen 3.6 Max (Preview) 1,460 Apr 2026 Official leaderboard
51 GLM-5 1,457 Feb 2026 Official leaderboard
52 GPT-6 Sol 1,457 max Sep 2026 Official leaderboard
53 Seed2.0 Pro 1,457 Feb 2026 Official leaderboard
54 Grok 4.6 1,456 high Aug 2026 Official leaderboard
55 Claude Sonnet 4.5 1,456 high, 32k Sep 2025 Official leaderboard
56 GPT-5.1 1,455 high Nov 2025 Official leaderboard
57 Qwen3.7-Plus 1,455 Jun 2026 Official leaderboard
58 Gemini 3.5 Flash-Lite 1,455 Jul 2026 Official leaderboard
59 Tencent Hy3 1,454 Jul 2026 Official leaderboard
60 GPT-5.6 Luna 1,453 xhigh Jul 2026 Official leaderboard
61 Gemma 4 31B IT 1,452 Apr 2026 Official leaderboard
62 GPT-5.3 Instant 1,450 Mar 2026 Official leaderboard
63 Claude Opus 4.1 1,450 thinking 16k Aug 2025 Official leaderboard
64 Kimi K2.5 1,450 thinking Jan 2026 Official leaderboard
65 Step 5 Preview 1,448 Sep 2026 Official leaderboard
66 MiMo-V2-Pro 1,448 Mar 2026 Official leaderboard
67 MiMo-V2.6 Flash 1,448 Sep 2026 Official leaderboard
68 GPT-5.4 Mini 1,447 high Mar 2026 Official leaderboard
69 Gemini 2.5 Pro Jun 2025 1,446 Jun 2025 Official leaderboard
70 GPT-4.5 1,445 Feb 2025 Official leaderboard
71 Inkling 1,443 Jul 2026 Official leaderboard
72 Qwen 3.6 Plus 1,443 Mar 2026 Official leaderboard
73 GPT-4o Mar 2025 1,443 Mar 2025 Official leaderboard
74 Grok 4.7 1,442 xhigh Sep 2026 Official leaderboard
75 Grok 4.3 1,442 Apr 2026 Official leaderboard
76 Qwen3.5 397B-A17B 1,441 Feb 2026 Official leaderboard
77 GLM-4.7 1,441 Dec 2025 Official leaderboard
78 GPT-6 Luna 1,441 max Sep 2026 Official leaderboard
79 DeepSeek-V4-Flash 1,439 high Apr 2026 Official leaderboard
80 Gemma 4 26B A4B 1,438 Jul 2026 Lab model card
81 GPT-5.2 1,437 high Dec 2025 Official leaderboard
82 MiniMax-M3 1,436 Jun 2026 Official leaderboard
83 GPT-5 1,435 high Aug 2025 Official leaderboard
84 Beam 1.0 1,435 Oct 2026 Official leaderboard
85 Qwen3-Max 1,434 Sep 2025 Official leaderboard
86 GLM-5V-Turbo 1,434 Apr 2026 Official leaderboard
87 MiMo-V2.5 1,434 Apr 2026 Official leaderboard
88 Qwen 3.8 27B 1,433 Aug 2026 Official leaderboard
89 Gemini 3.1 Flash-Lite 1,433 Mar 2026 Official leaderboard
90 o3 1,432 Apr 2025 Official leaderboard
91 Grok 4.1 Fast 1,431 reasoning Nov 2025 Official leaderboard
92 MiMo-V2-Omni 1,430 Mar 2026 Official leaderboard
93 GPT-5 Chat 1,427 Aug 2025 Official leaderboard
94 Mistral Medium 3.5 1,427 Apr 2026 Official leaderboard
95 Nemotron 3 Ultra 1,426 nvfp4 Jun 2026 Official leaderboard
96 Claude Opus 4 1,426 thinking 16k May 2025 Official leaderboard
97 DeepSeek-V3.2-Exp 1,425 thinking Sep 2025 Official leaderboard
98 DeepSeek-V3.2 1,425 Dec 2025 Official leaderboard
99 Muse Glimmer 1,425 Aug 2026 Official leaderboard
100 GLM-4.6 1,424 Sep 2025 Official leaderboard
101 Mistral Large 4 1,423 Oct 2026 Official leaderboard
102 Claude Haiku 5.5 1,422 high Oct 2026 Official leaderboard
103 Qwen3-235B-A22B-Instruct Jul 2025 1,422 Jul 2025 Official leaderboard
104 DeepSeek-R1 May 2025 1,421 May 2025 Official leaderboard
105 Nemotron 3.5 Super VL 1,420 Oct 2026 Lab model card
106 Grok 4 Fast 1,418 non-reasoning Sep 2025 Official leaderboard
107 Kimi K2 Sep 2025 1,418 Sep 2025 Official leaderboard
108 Mistral Large 3 1,418 Dec 2025 Lab model card
109 Kimi K2 Jul 2025 1,418 Jul 2025 Official leaderboard
110 DeepSeek-V3.1 1,417 Aug 2025 Official leaderboard
111 Qwen3.5-122B-A10B 1,416 Feb 2026 Official leaderboard
112 DeepSeek-V3.1-Terminus 1,416 thinking Sep 2025 Official leaderboard
113 MiniMax-M2.7 1,415 Mar 2026 Official leaderboard
114 GPT-4.1 1,415 Apr 2025 Official leaderboard
115 Claude Haiku 4.5 1,414 Oct 2025 Official leaderboard
116 Qwen3-VL-235B-A22B-Instruct 1,413 Sep 2025 Official leaderboard
117 Inkling 2 Small 1,412 Nov 2026 Official leaderboard
118 Grok 3 1,411 Apr 2025 Official leaderboard
119 GLM-4.5 1,411 Aug 2025 Official leaderboard
120 Grok 4 1,411 Jul 2025 Official leaderboard
121 Gemini 2.5 Flash Jun 2025 1,409 Jun 2025 Official leaderboard
122 Tencent Hy3 preview 1,409 Apr 2026 Official leaderboard
123 Qwen3.5-27B 1,409 Feb 2026 Official leaderboard
124 Mistral Medium 3.1 1,408 Aug 2025 Official leaderboard
125 Inkling-Small 1,405 Jul 2026 Official leaderboard
126 Gemini 2.5 Flash Sep 2025 1,403 Sep 2025 Official leaderboard
127 o1 1,402 Dec 2024 Official leaderboard
128 Qwen3-235B-A22B 1,402 non-thinking Apr 2025 Official leaderboard
129 Claude Sonnet 4 1,402 thinking 32k May 2025 Official leaderboard
130 GPT-5.4 Nano 1,401 high Mar 2026 Official leaderboard
131 LongCat-Flash-Chat 1,400 Aug 2025 Official leaderboard
132 Qwen3-235B-A22B-Thinking Jul 2025 1,400 Jul 2025 Official leaderboard
133 Qwen3-Next-80B-A3B-Instruct 1,399 Sep 2025 Official leaderboard
134 DeepSeek-R1 1,398 Jan 2025 Official leaderboard
135 Qwen3.5-Flash 1,396 Feb 2026 Official leaderboard
136 DeepSeek-V3 Mar 2025 1,395 Mar 2025 Official leaderboard
137 Qwen3-VL-235B-A22B 1,395 thinking Sep 2025 Official leaderboard
138 Qwen3.5-35B-A3B 1,394 Feb 2026 Official leaderboard
139 Step 3.5 Flash 1,393 Feb 2026 Official leaderboard
140 MiMo-V2-Flash 1,392 non-thinking Dec 2025 Official leaderboard
141 o4-mini 1,391 Apr 2025 Official leaderboard
142 MiniMax-M2.5 1,391 Feb 2026 Official leaderboard
143 GPT-5 mini 1,390 high Aug 2025 Official leaderboard
144 o1-preview 1,389 Sep 2024 Official leaderboard
145 Claude 3.7 Sonnet 1,388 thinking 32k Feb 2025 Official leaderboard
146 Qwen3-Coder-480B-A35B 1,388 Jul 2025 Official leaderboard
147 Solar Pro 4 1,387 Aug 2026 Official leaderboard
148 Hunyuan-T1 1,387 Mar 2025 Official leaderboard
149 Mistral Medium 3 1,387 May 2025 Official leaderboard
150 MiniMax-M2.1 1,384 Dec 2025 Official leaderboard
151 Hunyuan-TurboS 1,383 Feb 2025 Official leaderboard
152 GPT-4.1 mini 1,383 Apr 2025 Official leaderboard
153 Qwen3-30B-A3B-Instruct Jul 2025 1,382 Jul 2025 Official leaderboard
154 Gemini 2.5 Flash-Lite Sep 2025 1,379 non-thinking, 09-2025 Sep 2025 Official leaderboard
155 Trinity Large Preview 1,379 Jan 2026 Official leaderboard
156 GLM-4.6V 1,378 Dec 2025 Official leaderboard
157 Gemini 2.5 Flash-Lite Jun 2025 1,375 Jun 2025 Official leaderboard
158 Claude 3.5 Sonnet (October 2024) 1,374 Oct 2024 Official leaderboard
159 Qwen2.5-Max 1,374 Jan 2025 Official leaderboard
160 GLM-4.5-Air 1,373 Jul 2025 Official leaderboard
161 Qwen3-Next-80B-A3B 1,369 thinking Sep 2025 Official leaderboard
162 Trinity Large Thinking 1,367 Apr 2026 Official leaderboard
163 Gemma 3 27B 1,365 Mar 2025 Official leaderboard
164 glm-4.7-flash 1,364 Jan 2026 Official leaderboard
165 MiniMax-M1-80k 1,364 Jun 2025 Official leaderboard
166 Grok-3 mini 1,364 high Apr 2025 Official leaderboard
167 o3-mini 1,364 high Jan 2025 Official leaderboard
168 Gemini 2.0 Flash Feb 2025 1,360 Feb 2025 Official leaderboard
169 Nemotron 3 Super 1,360 Mar 2026 Official leaderboard
170 DeepSeek-V3 1,358 Dec 2024 Official leaderboard
171 Mistral Small 3.2 1,356 Jun 2025 Official leaderboard
172 INTELLECT-3 1,356 Nov 2025 Official leaderboard
173 Cohere Command A 1,354 Mar 2025 Official leaderboard
174 Gemini 2.0 Flash-Lite 1,354 Feb 2025 Official leaderboard
175 GLM-4.5V 1,352 Aug 2025 Official leaderboard
176 gpt-oss-120b 1,352 Aug 2025 Official leaderboard
177 Nemotron 3.5 Lightning 30B-A3B 1,351 nvfp4 Aug 2026 Official leaderboard
178 Gemini 1.5 Pro Sep 2024 1,351 Sep 2024 Official leaderboard
179 Step 3 1,349 Jul 2025 Official leaderboard
180 Llama-3.1-Nemotron-Ultra-253B-v1 1,348 Apr 2025 Official leaderboard
181 Qwen3-32B 1,347 Apr 2025 Official leaderboard
182 GPT-4o May 2024 1,346 May 2024 Official leaderboard
183 MiniMax-M2 1,344 Oct 2025 Official leaderboard
184 Claude 3.5 Sonnet 1,343 Jun 2024 Official leaderboard
185 Llama-3.3-Nemotron-Super-49B-v1.5 1,343 Jul 2025 Official leaderboard
186 Ling-flash-2.0 1,343 Sep 2025 Official leaderboard
187 Mercury 2 1,343 Feb 2026 Official leaderboard
188 Gemma 3 12B 1,342 Mar 2025 Official leaderboard
189 Granite 4.2 30B 1,340 Aug 2026 Official leaderboard
190 GPT-5 nano 1,338 high Aug 2025 Official leaderboard
191 o1-mini 1,337 Sep 2024 Official leaderboard
192 Grok-2 Aug 2024 1,336 Aug 2024 Official leaderboard
193 GPT-4o Aug 2024 1,336 Aug 2024 Official leaderboard
194 QwQ-32B 1,336 Mar 2025 Official leaderboard
195 Llama 3.1-405B 1,335 bf16 Jul 2024 Official leaderboard
196 Nova 2 Lite 1,335 Dec 2025 Official leaderboard
197 Olmo 3.1 32B Instruct 1,329 Dec 2025 Official leaderboard
198 Yi-Lightning 1,328 Dec 2024 Official leaderboard
199 Llama-3.3-Nemotron-Super-49B-v1 1,328 Mar 2025 Official leaderboard
200 Llama 4 Maverick 1,327 Apr 2025 Official leaderboard
201 Qwen3-30B-A3B 1,326 Apr 2025 Official leaderboard
202 Claude 3.5 Haiku 1,325 Oct 2024 Official leaderboard
203 GPT-4 Turbo Apr 2024 1,325 Apr 2024 Official leaderboard
204 Gemini 1.5 Pro May 2024 1,324 May 2024 Official leaderboard
205 DeepSeek-V2.5-1210 1,323 Dec 2024 Official leaderboard
206 Ring-flash-2.0 1,322 Sep 2025 Official leaderboard
207 GPT-4.1 nano 1,322 Apr 2025 Official leaderboard
208 Claude 3 Opus 1,322 Feb 2024 Official leaderboard
209 Llama 4 Scout 1,322 Apr 2025 Official leaderboard
210 Molmo2-8B 1,321 Dec 2025 Official leaderboard
211 Llama 3.3 70B Instruct 1,318 Dec 2024 Official leaderboard
212 GPT-4o mini 1,318 Jul 2024 Official leaderboard
213 gpt-oss-20b 1,318 Aug 2025 Official leaderboard
214 Gemma 3n E4B 1,317 Jun 2025 Official leaderboard
215 Mistral Large 2 Jul 2024 1,314 Jul 2024 Official leaderboard
216 Athene-V2-Chat 1,314 Nov 2024 Official leaderboard
217 Nemotron 3 Nano 30B-A3B 1,314 bf16 Dec 2025 Official leaderboard
218 GPT-4 Turbo (Jan 2024) 1,313 Jan 2024 Official leaderboard
219 GPT-4 Turbo Nov 2023 1,313 Nov 2023 Official leaderboard
220 Gemini 1.5 Flash Sep 2024 1,309 Aug 2024 Official leaderboard
221 Grok-2 mini 1,308 Aug 2024 Official leaderboard
222 DeepSeek-V2.5 Sep 2024 1,307 Sep 2024 Official leaderboard
223 Athene-70B 1,307 Jul 2024 Official leaderboard
224 Olmo 3 32B Think 1,306 Nov 2025 Official leaderboard
225 Mistral Large 2 Nov 2024 1,306 Nov 2024 Official leaderboard
226 Mercury 1,305 Jun 2025 Official leaderboard
227 Magistral Medium 1.0 1,305 Jun 2025 Official leaderboard
228 Granite 4.1 8B 1,304 Apr 2026 Official leaderboard
229 Gemma 3 4B 1,303 Mar 2025 Official leaderboard
230 Qwen2.5-72B 1,303 Sep 2024 Official leaderboard
231 Mistral Small 3.1 1,303 Mar 2025 Official leaderboard
232 Llama-3.1-Nemotron-70B-Instruct 1,299 Oct 2024 Official leaderboard
233 Llama 3.1-70B 1,293 Jul 2024 Official leaderboard
234 Amazon Nova Pro 1,290 Dec 2024 Official leaderboard
235 Gemma 2 27B 1,290 Jun 2024 Official leaderboard
236 Granite 4.2 8B 1,290 Aug 2026 Official leaderboard
237 Jamba 1.5 Large 1,290 Aug 2024 Official leaderboard
238 Granite 4.2 3B 1,289 Aug 2026 Official leaderboard
239 Reka Core 1,288 Apr 2024 Official leaderboard
240 GPT-4 Mar 2023 1,288 Mar 2023 Official leaderboard
241 Granite 4.0 H Small 1,287 Oct 2025 Official leaderboard
242 Llama-3.1-Nemotron-51B-Instruct 1,287 Sep 2024 Official leaderboard
243 Gemini 1.5 Flash May 2024 1,287 May 2024 Official leaderboard
244 Tulu 3 (Tülu 3) 70B 1,286 Nov 2024 Official leaderboard
245 Olmo 3.1 32B Think 1,286 Dec 2025 Official leaderboard
246 Claude 3 Sonnet 1,281 Feb 2024 Official leaderboard
247 Nemotron-4-340B-Instruct 1,277 Jun 2024 Official leaderboard
248 Llama 3-70B 1,277 Apr 2024 Official leaderboard
249 GPT-4 Jun 2023 1,276 Jun 2023 Official leaderboard
250 Command R+ 1,276 Aug 2024 Official leaderboard
251 Mistral Small 3 1,274 Jan 2025 Official leaderboard
252 Reka Flash 1,273 Feb 2024 Official leaderboard
253 Qwen2.5-Coder-32B-Instruct 1,271 Nov 2024 Official leaderboard
254 Aya Expanse 32B 1,267 Oct 2024 Official leaderboard
255 Gemma 2 9B 1,267 Jun 2024 Official leaderboard
256 DeepSeek-Coder-V2 236B 1,266 Jun 2024 Official leaderboard
257 Qwen2-72B 1,262 Jun 2024 Official leaderboard
258 Claude 3 Haiku 1,262 Mar 2024 Official leaderboard
259 Amazon Nova Lite 1,260 Dec 2024 Official leaderboard
260 Gemini 1.5 Flash 8B 1,259 Oct 2024 Official leaderboard
261 Phi-4 1,256 Dec 2024 Official leaderboard
262 OLMo 2 32B Instruct 1,252 Mar 2025 Official leaderboard
263 c4ai-command-r-08-2024 1,251 Aug 2024 Official leaderboard
264 Mistral Large 1,243 Feb 2024 Official leaderboard
265 Amazon Nova Micro 1,241 Dec 2024 Official leaderboard
266 Jamba 1.5 Mini 1,240 Aug 2024 Official leaderboard
267 Ministral 8B 1,238 Oct 2024 Official leaderboard
268 Gemini 1.0 Pro 1,237 Dec 2023 Official leaderboard
269 Qwen1.5-110B 1,234 Apr 2024 Official leaderboard
270 Qwen1.5-72B 1,234 Feb 2024 Official leaderboard
271 Mixtral 8x22B 1,230 Apr 2024 Official leaderboard
272 Command R (03-2024) 1,227 Mar 2024 Official leaderboard
273 GPT-3.5 Turbo Jan 2024 1,226 Jan 2024 Official leaderboard
274 Llama 3-8B 1,224 Apr 2024 Official leaderboard
275 Aya Expanse 8B 1,223 Oct 2024 Official leaderboard
276 Mistral Medium 1,223 Dec 2023 Official leaderboard
277 Llama-3.1-Tulu-3-8B 1,221 Nov 2024 Official leaderboard
278 Zephyr ORPO 141B A35B v0.1 1,213 Apr 2024 Official leaderboard
279 Yi-1.5-34B 1,213 May 2024 Official leaderboard
280 Llama 3.1-8B 1,211 Jul 2024 Official leaderboard
281 Granite-3.1-8B-Instruct 1,209 Dec 2024 Official leaderboard
282 GPT-3.5 Turbo Nov 2023 1,204 Nov 2023 Official leaderboard
283 Qwen1.5-32B 1,204 Feb 2024 Official leaderboard
284 Gemma 2 2B IT 1,200 Jul 2024 Official leaderboard
285 phi-3-medium 14B 1,198 Apr 2024 Official leaderboard
286 Mixtral 8x7B 1,197 Dec 2023 Official leaderboard
287 DBRX 1,196 Mar 2024 Official leaderboard
288 Qwen1.5-14B 1,191 Feb 2024 Official leaderboard
289 InternLM2.5-20B-Chat 1,191 Aug 2024 Official leaderboard
290 DeepSeek LLM 67B 1,185 Nov 2023 Official leaderboard
291 Yi-34B 1,184 Nov 2023 Official leaderboard
292 Granite-3.0-8B-Instruct 1,183 Oct 2024 Official leaderboard
293 Gemma 1.1 7B IT 1,183 Apr 2024 Official leaderboard
294 Snowflake Arctic Instruct 1,180 Apr 2024 Official leaderboard
295 Granite-3.1-2B-Instruct 1,179 Dec 2024 Official leaderboard
296 Tulu 2 DPO 70B 1,178 Nov 2023 Official leaderboard
297 phi-3-small 7.4B 1,171 Apr 2024 Official leaderboard
298 Starling-LM-7B-beta 1,171 Mar 2024 Official leaderboard
299 Llama 2-70B 1,171 Jul 2023 Official leaderboard
300 Starling-LM-7B-alpha 1,168 Nov 2023 Official leaderboard
301 Llama 3.2 3B 1,167 Sep 2024 Official leaderboard
302 Nous-Hermes-2-Mixtral-8x7B-DPO 1,164 Jan 2024 Official leaderboard
303 Granite-3.0-2B-Instruct 1,157 Oct 2024 Official leaderboard
304 Llama2-70B-SteerLM-Chat 1,155 Nov 2023 Official leaderboard
305 QwQ-32B-Preview 1,154 Nov 2024 Official leaderboard
306 SOLAR-10.7B-Instruct-v1.0 1,153 Dec 2023 Official leaderboard
307 MPT-30B 1,151 Jun 2023 Official leaderboard
308 Mistral 7B v0.2 1,149 Dec 2023 Official leaderboard
309 Falcon-180B 1,148 Sep 2023 Official leaderboard
310 Qwen1.5-7B 1,144 Feb 2024 Official leaderboard
311 Llama 2-13B 1,142 Jul 2023 Official leaderboard
312 Qwen-14B 1,140 Sep 2023 Official leaderboard
313 Gemma 7B 1,138 Feb 2024 Official leaderboard
314 Code Llama 34B Instruct 1,137 Aug 2023 Official leaderboard
315 Zephyr 7B Beta 1,131 Oct 2023 Official leaderboard
316 Phi-3-mini-128k-instruct 1,130 Apr 2024 Official leaderboard
317 phi-3-mini 3.8B 1,128 Apr 2024 Official leaderboard
318 Zephyr 7B Alpha 1,127 Oct 2023 Official leaderboard
319 Code Llama 70B Instruct 1,119 Jan 2024 Official leaderboard
320 Gemma 1.1 2B IT 1,117 Apr 2024 Official leaderboard
321 SmolLM2 1.7B Instruct 1,115 Oct 2024 Official leaderboard
322 Llama 3.2 1B 1,111 Sep 2024 Official leaderboard
323 Mistral-7B-Instruct-v0.1 1,111 Sep 2023 Official leaderboard
324 Llama 2-7B 1,108 Jul 2023 Official leaderboard
325 Gemma 2B 1,094 Feb 2024 Official leaderboard
326 Qwen1.5-4B-Chat 1,091 Feb 2024 Official leaderboard
327 OLMo-7B-Instruct 1,074 Feb 2024 Official leaderboard
328 MPT-7B 1,064 May 2023 Official leaderboard
329 ChatGLM3-6B 1,057 Oct 2023 Official leaderboard
330 Mistral 7B v0.1 1,031 Oct 2023 Lab model card
331 chatglm2-6b 1,025 Jun 2023 Official leaderboard
332 ChatGLM-6B 996 Mar 2023 Official leaderboard
333 FastChat-T5-3B 993 Apr 2023 Official leaderboard
334 Dolly 2.0-12b 983 Apr 2023 Official leaderboard
335 LLaMA-13B 975 Feb 2023 Official leaderboard
336 stablelm-tuned-alpha-7b 953 Apr 2023 Official leaderboard

Labs report scores for 14 models in their cards. Switch the scores above to rank them together.

More effort adds a median 2 elo

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 4.6
high
1,503
Claude Opus 4.7
high
1,501
Claude Opus 5
high
1,490
Claude Opus 4.8
high
1,482
GPT-5.5
high
1,481
Gemini 3.5 Flash
medium
1,478
GPT-5.4
high
1,475
Claude Opus 4.5
high, 32k
1,474
Gemini 3 Flash
minimal
1,473
Grok 4.1
thinking
1,465
DeepSeek-V4-Pro
high high
1,464
Claude Sonnet 4.5
high, 32k
1,456

Source: Official LMArena (Elo) leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Carbon high 1,526
Gemini 4 Argon high 1,522
Muse Wonder max 1,511
Claude Opus 5.5 high 1,506
Claude Fable 5 high 1,504
Claude Opus 4.6 high 1,503
Claude Fable 5.1 max 1,503
Claude Opus 4.7 high 1,501
Gemini 3.8 Flash high 1,497
Claude Opus 4.6 1,496
Muse Spark 1.3 max 1,496
Claude Opus 4.7 1,494
Muse Spark 1.2 xhigh 1,493
Muse Spark 1.1 1,491
Claude Opus 5 high 1,490
Gemini 3.7 Flash high 1,489
Muse Spark 1,489
Claude Opus 5 max 1,489
Kimi K3 max 1,487
Gemini 3.1 Pro 1,487
Gemini 3 Pro 1,486
GPT-5.6 Sol xhigh 1,485
Qwen 3.8 Max 1,484
Kimi K3.1 Pro max 1,483
Gemini 3.6 Flash high 1,483
GLM-5.3 max 1,483
GPT-6.1 Sol max 1,482
Claude Opus 4.8 high 1,482
GPT-5.5 high 1,481
MiMo-V2.6 Pro 1,480
Gemini 3.5 Flash high 1,478
Gemini 3.5 Flash medium 1,476
GPT-5.5 1,476
GPT-5.2 Instant 1,476
GPT-5.4 high 1,475
GLM-5.2 max 1,475
DeepSeek V4.1 Flash max 1,475
Claude Opus 4.8 1,474
GLM-5.3-Flash 1,474
GPT-6 Astra max 1,474
Qwen3.7-Max 1,474
Claude Opus 4.5 high, 32k 1,474
GPT-5.5 Instant 1,473
Gemini 3 Flash 1,473
Claude Sonnet 5.5 xhigh 1,472
Claude Sonnet 4.6 1,472
Claude Opus 4.5 1,470
GPT-5.6 Terra xhigh 1,468
ERNIE 5.1 1,467
MiMo-V2.5-Pro 1,467
Grok 4.5 1,466
Grok 4.1 thinking 1,465
GLM-5.1 1,465
GPT-5.4 1,465
DeepSeek-V4-Pro high 1,464
Claude Sonnet 5 high 1,461
Kimi K2.6 1,461
Qwen 3.6 Max (Preview) 1,460
Grok 4.1 1,459
Gemini 3 Flash minimal 1,458
DeepSeek-V4-Pro 1,458
GLM-5 1,457
GPT-6 Sol max 1,457
Seed2.0 Pro 1,457
Grok 4.6 high 1,456
Claude Sonnet 4.5 high, 32k 1,456
GPT-5.1 high 1,455
Qwen3.7-Plus 1,455
Claude Sonnet 4.5 1,455
DeepSeek-V4-Pro high 1,455
Gemini 3.5 Flash-Lite 1,455
Tencent Hy3 1,454
GPT-5.6 Luna xhigh 1,453
Gemma 4 31B IT 1,452
GPT-5.3 Instant 1,450
Claude Opus 4.1 thinking 16k 1,450
Kimi K2.5 thinking 1,450
Step 5 Preview 1,448
MiMo-V2-Pro 1,448
Claude Opus 4.1 1,448
MiMo-V2.6 Flash 1,448
GPT-5.4 Mini high 1,447
Gemini 2.5 Pro Jun 2025 1,446
GPT-4.5 1,445
Inkling 1,443
Qwen 3.6 Plus 1,443
GPT-4o Mar 2025 1,443
Grok 4.7 xhigh 1,442
Grok 4.3 1,442
Qwen3.5 397B-A17B 1,441
GLM-4.7 1,441
GPT-6 Luna max 1,441
DeepSeek-V4-Flash high 1,439
GPT-5.1 1,439
Gemma 4 26B A4B 1,437
GPT-5.2 high 1,437
MiniMax-M3 1,436
DeepSeek-V4-Flash 1,436
GPT-5.2 1,435
GPT-5 high 1,435
Beam 1.0 1,435
Qwen3-Max 1,434
GLM-5V-Turbo 1,434
MiMo-V2.5 1,434
Qwen 3.8 27B 1,433
Gemini 3.1 Flash-Lite 1,433
o3 1,432
Kimi K2.5 instant 1,431
Grok 4.1 Fast reasoning 1,431
MiMo-V2-Omni 1,430
GPT-5 Chat 1,427
Mistral Medium 3.5 1,427
Nemotron 3 Ultra nvfp4 1,426
Claude Opus 4 thinking 16k 1,426
DeepSeek-V3.2-Exp thinking 1,425
DeepSeek-V3.2 1,425
Muse Glimmer 1,425
GLM-4.6 1,424
Qwen3-Max 1,423
Mistral Large 4 1,423
DeepSeek-V3.2 thinking 1,423
Claude Haiku 5.5 high 1,422
Qwen3-235B-A22B-Instruct Jul 2025 1,422
DeepSeek-V3.2-Exp 1,422
DeepSeek-R1 May 2025 1,421
Grok 4 Fast non-reasoning 1,418
Kimi K2 Sep 2025 1,418
Kimi K2 Jul 2025 1,418
DeepSeek-V3.1 1,417
Qwen3.5-122B-A10B 1,416
DeepSeek-V3.1-Terminus thinking 1,416
DeepSeek-V3.1 thinking 1,416
Nemotron 3.5 Super VL nvfp4 1,415
MiniMax-M2.7 1,415
DeepSeek-V3.1-Terminus 1,415
Mistral Large 3 1,415
GPT-4.1 1,415
Claude Opus 4 1,414
Claude Haiku 4.5 1,414
Qwen3-VL-235B-A22B-Instruct 1,413
Inkling 2 Small 1,412
Grok 3 1,411
GLM-4.5 1,411
Grok 4 1,411
Gemini 2.5 Flash Jun 2025 1,409
Tencent Hy3 preview 1,409
Qwen3.5-27B 1,409
Mistral Medium 3.1 1,408
Inkling-Small 1,405
Grok 4 Fast reasoning 1,405
Gemini 2.5 Flash Sep 2025 1,403
o1 1,402
Qwen3-235B-A22B non-thinking 1,402
Claude Sonnet 4 thinking 32k 1,402
GPT-5.4 Nano high 1,401
LongCat-Flash-Chat 1,400
Qwen3-235B-A22B-Thinking Jul 2025 1,400
Qwen3-Next-80B-A3B-Instruct 1,399
DeepSeek-R1 1,398
Qwen3.5-Flash 1,396
DeepSeek-V3 Mar 2025 1,395
Qwen3-VL-235B-A22B thinking 1,395
Qwen3.5-35B-A3B 1,394
Step 3.5 Flash 1,393
MiMo-V2-Flash non-thinking 1,392
Claude Sonnet 4 1,391
o4-mini 1,391
MiniMax-M2.5 1,391
GPT-5 mini high 1,390
o1-preview 1,389
Claude 3.7 Sonnet thinking 32k 1,388
Qwen3-Coder-480B-A35B 1,388
Solar Pro 4 1,387
Hunyuan-T1 1,387
Mistral Medium 3 1,387
MiMo-V2-Flash thinking 1,386
MiniMax-M2.1 1,384
Hunyuan-TurboS 1,383
GPT-4.1 mini 1,383
Qwen3-30B-A3B-Instruct Jul 2025 1,382
Gemini 2.5 Flash-Lite Sep 2025 non-thinking, 09-2025 1,379
Trinity Large Preview 1,379
GLM-4.6V 1,378
Gemini 2.5 Flash-Lite Jun 2025 1,375
Qwen3-235B-A22B 1,375
Claude 3.5 Sonnet (October 2024) 1,374
Qwen2.5-Max 1,374
GLM-4.5-Air 1,373
Claude 3.7 Sonnet 1,372
Qwen3-Next-80B-A3B thinking 1,369
Trinity Large Thinking 1,367
Gemma 3 27B 1,365
glm-4.7-flash 1,364
MiniMax-M1-80k 1,364
Grok-3 mini high 1,364
o3-mini high 1,364
Gemini 2.0 Flash Feb 2025 1,360
Nemotron 3 Super 1,360
DeepSeek-V3 1,358
Grok-3 mini 1,358
Mistral Small 3.2 1,356
INTELLECT-3 1,356
Cohere Command A 1,354
Gemini 2.0 Flash-Lite 1,354
GLM-4.5V 1,352
gpt-oss-120b 1,352
Nemotron 3.5 Lightning 30B-A3B nvfp4 1,351
Gemini 1.5 Pro Sep 2024 1,351
Hunyuan-TurboS 1,349
Step 3 1,349
o3-mini 1,348
Llama-3.1-Nemotron-Ultra-253B-v1 1,348
Qwen3-32B 1,347
GPT-4o May 2024 1,346
MiniMax-M2 1,344
Claude 3.5 Sonnet 1,343
Llama-3.3-Nemotron-Super-49B-v1.5 1,343
Ling-flash-2.0 1,343
Mercury 2 1,343
Gemma 3 12B 1,342
Granite 4.2 30B 1,340
GPT-5 nano high 1,338
o1-mini 1,337
Grok-2 Aug 2024 1,336
GPT-4o Aug 2024 1,336
QwQ-32B 1,336
Llama 3.1-405B bf16 1,335
Nova 2 Lite 1,335
Llama 3.1-405B fp8 1,334
Olmo 3.1 32B Instruct 1,329
Yi-Lightning 1,328
Llama-3.3-Nemotron-Super-49B-v1 1,328
Llama 4 Maverick 1,327
Qwen3-30B-A3B 1,326
Claude 3.5 Haiku 1,325
GPT-4 Turbo Apr 2024 1,325
Gemini 1.5 Pro May 2024 1,324
DeepSeek-V2.5-1210 1,323
Ring-flash-2.0 1,322
GPT-4.1 nano 1,322
Claude 3 Opus 1,322
Llama 4 Scout 1,322
Molmo2-8B 1,321
Llama 3.3 70B Instruct 1,318
GPT-4o mini 1,318
gpt-oss-20b 1,318
Gemma 3n E4B 1,317
Mistral Large 2 Jul 2024 1,314
Athene-V2-Chat 1,314
Nemotron 3 Nano 30B-A3B bf16 1,314
GPT-4 Turbo (Jan 2024) 1,313
GPT-4 Turbo Nov 2023 1,313
Gemini 1.5 Flash Sep 2024 1,309
Grok-2 mini 1,308
DeepSeek-V2.5 Sep 2024 1,307
Athene-70B 1,307
Olmo 3 32B Think 1,306
Mistral Large 2 Nov 2024 1,306
Mercury 1,305
Magistral Medium 1.0 1,305
Granite 4.1 8B 1,304
Gemma 3 4B 1,303
Qwen2.5-72B 1,303
Mistral Small 3.1 1,303
Llama-3.1-Nemotron-70B-Instruct 1,299
Llama 3.1-70B 1,293
Amazon Nova Pro 1,290
Gemma 2 27B 1,290
Granite 4.2 8B 1,290
Jamba 1.5 Large 1,290
Granite 4.2 3B 1,289
Reka Core 1,288
GPT-4 Mar 2023 1,288
Granite 4.0 H Small 1,287
Llama-3.1-Nemotron-51B-Instruct 1,287
Gemini 1.5 Flash May 2024 1,287
Tulu 3 (Tülu 3) 70B 1,286
Olmo 3.1 32B Think 1,286
Claude 3 Sonnet 1,281
Nemotron-4-340B-Instruct 1,277
Llama 3-70B 1,277
GPT-4 Jun 2023 1,276
Command R+ 1,276
Mistral Small 3 1,274
Reka Flash 1,273
Qwen2.5-Coder-32B-Instruct 1,271
Aya Expanse 32B 1,267
Gemma 2 9B 1,267
DeepSeek-Coder-V2 236B 1,266
Qwen2-72B 1,262
Command R+ 1,262
Claude 3 Haiku 1,262
Amazon Nova Lite 1,260
Gemini 1.5 Flash 8B 1,259
Phi-4 1,256
OLMo 2 32B Instruct 1,252
c4ai-command-r-08-2024 1,251
Mistral Large 1,243
Amazon Nova Micro 1,241
Jamba 1.5 Mini 1,240
Ministral 8B 1,238
Gemini 1.0 Pro 1,237
Qwen1.5-110B 1,234
Qwen1.5-72B 1,234
Mixtral 8x22B 1,230
Command R (03-2024) 1,227
Reka Flash 1,227
GPT-3.5 Turbo Jan 2024 1,226
Gemini 1.0 Pro 1,224
Llama 3-8B 1,224
Aya Expanse 8B 1,223
Mistral Medium 1,223
Llama-3.1-Tulu-3-8B 1,221
Zephyr ORPO 141B A35B v0.1 1,213
Yi-1.5-34B 1,213
Llama 3.1-8B 1,211
Granite-3.1-8B-Instruct 1,209
GPT-3.5 Turbo Nov 2023 1,204
Qwen1.5-32B 1,204
Gemma 2 2B IT 1,200
phi-3-medium 14B 1,198
Mixtral 8x7B 1,197
DBRX 1,196
Qwen1.5-14B 1,191
InternLM2.5-20B-Chat 1,191
DeepSeek LLM 67B 1,185
Yi-34B 1,184
Granite-3.0-8B-Instruct 1,183
Gemma 1.1 7B IT 1,183
Snowflake Arctic Instruct 1,180
Granite-3.1-2B-Instruct 1,179
Tulu 2 DPO 70B 1,178
phi-3-small 7.4B 1,171
Starling-LM-7B-beta 1,171
Llama 2-70B 1,171
Starling-LM-7B-alpha 1,168
Llama 3.2 3B 1,167
Nous-Hermes-2-Mixtral-8x7B-DPO 1,164
Granite-3.0-2B-Instruct 1,157
Llama2-70B-SteerLM-Chat 1,155
QwQ-32B-Preview 1,154
SOLAR-10.7B-Instruct-v1.0 1,153
MPT-30B 1,151
Mistral 7B v0.2 1,149
Falcon-180B 1,148
Qwen1.5-7B 1,144
Llama 2-13B 1,142
Qwen-14B 1,140
Gemma 7B 1,138
Code Llama 34B Instruct 1,137
Zephyr 7B Beta 1,131
Phi-3-mini-128k-instruct 1,130
phi-3-mini 3.8B 1,128
Zephyr 7B Alpha 1,127
Code Llama 70B Instruct 1,119
Gemma 1.1 2B IT 1,117
SmolLM2 1.7B Instruct 1,115
Llama 3.2 1B 1,111
Mistral-7B-Instruct-v0.1 1,111
Llama 2-7B 1,108
Gemma 2B 1,094
Qwen1.5-4B-Chat 1,091
OLMo-7B-Instruct 1,074
MPT-7B 1,064
ChatGLM3-6B 1,057
chatglm2-6b 1,025
ChatGLM-6B 996
FastChat-T5-3B 993
Dolly 2.0-12b 983
LLaMA-13B 975
stablelm-tuned-alpha-7b 953

19 models have held number one on the official leaderboard since its release in May 2023 19 models have held number one with claims included since its release in May 2023

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.

OpenAI Anthropic Google DeepMind xAI Mistral AI Moonshot AI
Own leaderboard 19 leaders
Lab claims 6 leaders
Kimi K3 1,486

Sources: Official LMArena (Elo) leaderboard and labs’ model cards

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card
800 1,000 1,200 1,400 1,600 2023 2024 2025 2026 2027 800 1,000 1,200 1,400 1,600 2023 2024 2025 2026 2027

Sources: Official LMArena (Elo) leaderboard and labs’ model cards

Labs headline it less often now, last in March 2026

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

xAI
Qwen
Mistral AI
Google DeepMind
DateLaunch postScoreAs the post writes it
Mar 3, 2026 Gemini 3.1 Flash-Lite 1432 Elo 1432 on the Arena.ai leaderboard, quoted in the Gemini 3.1 Flash-Lite launch blog
Dec 2, 2025 Mistral Large 3 1418 LMArena ELO Score (+/- 11)
Nov 17, 2025 Grok 4.1 1483 LMArena Text Leaderboard overall Elo (Grok 4.1 Thinking, 'quasarflux')
Sep 24, 2025 Qwen3-Max LMArena Text Arena
Feb 19, 2025 Grok 3 1402 Chatbot Arena Score (early Grok 3 'chocolate')
Aug 13, 2024 Grok-2 LMSYS leaderboard overall Elo (early Grok-2 as 'sus-column-r')

13 system cards report it, from 5 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Oct 15, 2026 Nemotron 3.5 Super VL technical report 1420 Text Arena, Overall, With Style Control, 1420 +/- 12, 2,328 votes, preliminary NVFP4 (Table 11) Capabilities
Jul 27, 2026 Kimi K3 technical report 1486 Text Arena (Elo), rank 8 of 200 (Table 5) Other
Jul 24, 2026 Gemma 4 31B IT technical report 1451 Arena Text Elo, as of June 19, 2026 (Table 4) Capabilities
Jul 24, 2026 Gemma 4 26B A4B technical report 1438 Arena Text Elo, as of June 19, 2026 (Table 4) Capabilities
Feb 17, 2026 GLM-5 technical report 1452 LMArena Text Arena score, rank 11 (Figure 3 screenshot); LMsys Chatbot Arena 1452 (Figure 11) Capabilities
Jul 21, 2025 Kimi K2 technical report LMSYS Arena text leaderboard as of 2025-07-17: top open-source model and 5th overall, no rating printed (Appendix C) Capabilities
Jul 7, 2025 Gemini 2.5 Pro technical report LMArena score, plotted in Figure 1 without printed value; text says +122 points over Gemini 1.5 Pro Capabilities
Jul 7, 2025 Gemini 2.5 Flash technical report LMArena score, plotted in Figure 1 without printed value; text says +111 points over Gemini 1.5 Flash Capabilities
Mar 25, 2025 Gemma 3 27B technical report 1338 Chatbot Arena Elo, IT, preliminary results received March 8, 2025 (Table 5) Capabilities
Jul 31, 2024 Gemma 2 9B technical report 1187 LMSYS Chatbot Arena Elo, IT (Table 14) Capabilities
Jul 31, 2024 Gemma 2 27B technical report 1218 LMSYS Chatbot Arena Elo, IT (Table 14) Capabilities
Jan 8, 2024 Mixtral 8x7B technical report 1121 LMSys Arena Elo, Mixtral 8x7B Instruct v0.1, screenshot Dec 22, 2023 (Figure 6 caption) Capabilities
Oct 10, 2023 Mistral 7B v0.1 technical report 1031 Chatbot Arena ELO Rating, Mistral 7B Instruct (Table 3) Capabilities

13 lab claims next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. Every benchmark.

Model Lab says Board says Gap What differs
Mixtral 8x7B 1,121 LMSys Arena Elo, Mixtral 8x7B Instruct v0.1, screenshot Dec 22, 2023 (Figure 6 caption) 1,197 Leaderboard −76 Mistral quotes Arena's December 2023 rating, while the board reports a later rating from its updated vote pool and scoring method.
Gemma 2 9B 1,187 LMSYS Chatbot Arena Elo, IT (Table 14) 1,267 Leaderboard −80 Google quotes Arena's 2024 rating, while the board reflects later votes and rating adjustments.
Gemma 2 27B 1,218 LMSYS Chatbot Arena Elo, IT (Table 14) 1,290 Leaderboard −72 The lab quotes a July 2024 Arena rating, while the board uses a November 2026 rating with style controls.
Gemma 3 27B 1,338 Chatbot Arena Elo, IT, preliminary results received March 8, 2025 (Table 5) 1,365 Leaderboard −27 Google reports a preliminary March 2025 Arena rating, while the board reports a later rating from updated votes.
Grok 4.1 1,483 LMArena Text Leaderboard overall Elo (Grok 4.1 Thinking, 'quasarflux') 1,465 Leaderboard, thinking +18 xAI quotes Grok 4.1 Thinking's launch rating, while the board reports its later Arena rating.
Grok 3 1,402 Chatbot Arena Score (early Grok 3 'chocolate') 1,411 Leaderboard −9 The lab quotes the early chocolate model snapshot, while the board rates the later Grok 3 Preview release with style controls.
GLM-5 1,452 LMArena Text Arena score, rank 11 (Figure 3 screenshot); LMsys Chatbot Arena 1452 (Figure 11) 1,457 Leaderboard −5 Z.ai quotes an earlier Arena rating, while the board reports a later rating from updated votes and scoring.
Nemotron 3.5 Super VL 1,420 Text Arena, Overall, With Style Control, 1420 +/- 12, 2,328 votes, preliminary NVFP4 (Table 11) 1,415 Leaderboard, nvfp4 +5 NVIDIA reports a preliminary Arena rating from 2,328 votes, while the board reports a later rating.
Mistral Large 3 1,418 LMArena ELO Score (+/- 11) 1,415 Leaderboard +3 Mistral quotes its December 2025 Arena rating, while the board reflects a later rating snapshot.
Kimi K3 1,486 Text Arena (Elo), rank 8 of 200 (Table 5) 1,487 Leaderboard, max −1 Moonshot quotes Arena's July 23 rating, while the board reports a later rating as votes accumulate.
Gemini 3.1 Flash-Lite 1,432 Elo 1432 on the Arena.ai leaderboard, quoted in the Gemini 3.1 Flash-Lite launch blog 1,433 Leaderboard −1
Gemma 4 31B IT 1,451 Arena Text Elo, as of June 19, 2026 (Table 4) 1,452 Leaderboard −1 Google quotes Arena's June 19 rating, while the board reflects a later snapshot with more votes.
Gemma 4 26B A4B 1,438 Arena Text Elo, as of June 19, 2026 (Table 4) 1,437 Leaderboard +1 The lab quotes a rounded June 19 Arena rating, while the board uses the November 8 rating.

More in Instructions and chat

All 81 in Instructions and chat
  • IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy. Gemma 4 31B IT 98.9%
  • IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Nemotron-Cascade 2 30B-A3B 82.9%
  • MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
  • Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
  • AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics. MAI-Thinking-1 85%
  • IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. Gemma 4 31B IT 95.9%