Benchmark Almanac

DesignArena Full Stack

Claude Opus 5.5 1,393 leads since September 2026
Not in model cards

Coding agents build complete React apps with sign-in, databases and backend code from real user prompts. Users try the apps and vote for the better one.

DesignArena published a Fullstack Arena methodology post. One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Building whole projects
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
49
Models scored on its own leaderboard

Claude Opus 5.5 leads with 1,393

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

49 models. Scroll sideways for the rest. Bars start at 900.

  1. 1,393 Claude Opus 5.5
  2. 1,339 GPT-6 Astra
  3. 1,328 Kimi K3.1 Pro
  4. 1,304 Claude Fable 5.1
  5. 1,295 Kimi K3
  6. 1,292 Muse Spark 1.3
  7. 1,285 Claude Opus 5
  8. 1,283 Qwen 3.8 Max
  9. 1,259 Claude Fable 5
  10. 1,242 Grok 4.6
  11. 1,237 GPT-5.6 Sol
  12. 1,227 Claude Opus 4.8
  13. 1,227 Claude Sonnet 5
  14. 1,227 Grok 4.5
  15. 1,220 Gemini 3.8 Flash
  16. 1,219 GLM-5.2
  17. 1,214 GPT-6 Sol
  18. 1,199 Claude Opus 4.6
  19. 1,191 Claude Sonnet 4.6
  20. 1,188 Muse Spark 1.2
  21. 1,188 Gemini 3.7 Flash
  22. 1,179 MiniMax-M3
  23. 1,175 Gemini 3.5 Flash
  24. 1,175 Muse Spark 1.1
  25. 1,172 Qwen3.7-Max
  26. 1,159 Gemini 3.6 Flash
  27. 1,154 Kimi K2.7 Code
  28. 1,145 GLM-5.1
  29. 1,140 GPT-6 Luna
  30. 1,135 Claude Opus 4.5
  31. 1,134 Kimi K2.6
  32. 1,128 GLM-5V-Turbo
  33. 1,101 GLM-5
  34. 1,092 Kimi K2.5
  35. 1,068 GPT-5.5
  36. 1,053 Gemini 3 Pro
  37. 1,046 Gemini 3.1 Pro
  38. 1,042 Gemini 3 Flash
  39. 1,041 GPT-5.6 Terra
  40. 1,033 Grok 4.20
  41. 1,029 Claude Sonnet 4.5
  42. 1,028 GLM-4.7
  43. 1,021 GPT-5.2
  44. 1,008 GLM-4.6
  45. 996 GPT-5.4
  46. 988 grok-code-fast-1
  47. 986 Grok 4.3
  48. 972 GPT-5.2 Codex
  49. 962 GPT-5.3 Codex

Bars start at 900.

  1. 1 Claude Opus 5.5 1,393
  2. 2 GPT-6 Astra xhigh 1,339
  3. 3 Kimi K3.1 Pro 1,328
  4. 4 Claude Fable 5.1 1,304
  5. 5 Kimi K3 1,295
  6. 6 Muse Spark 1.3 xhigh, max 1,292
  7. 7 Claude Opus 5 1,285
  8. 8 Qwen 3.8 Max 1,283
  9. 9 Claude Fable 5 1,259
  10. 10 Grok 4.6 1,242
  11. 11 GPT-5.6 Sol medium, xhigh 1,237
  12. 12 Claude Opus 4.8 1,227
  13. 13 Claude Sonnet 5 1,227
  14. 14 Grok 4.5 1,227
  15. 15 Gemini 3.8 Flash 1,220
  16. 16 GLM-5.2 1,219
  17. 17 GPT-6 Sol 1,214
  18. 18 Claude Opus 4.6 1,199
  19. 19 Claude Sonnet 4.6 1,191
  20. 20 Muse Spark 1.2 1,188
  21. 21 Gemini 3.7 Flash 1,188
  22. 22 MiniMax-M3 1,179
  23. 23 Gemini 3.5 Flash 1,175
  24. 24 Muse Spark 1.1 1,175
  25. 25 Qwen3.7-Max 1,172
  26. 26 Gemini 3.6 Flash 1,159
  27. 27 Kimi K2.7 Code 1,154
  28. 28 GLM-5.1 1,145
  29. 29 GPT-6 Luna 1,140
  30. 30 Claude Opus 4.5 1,135
  31. 31 Kimi K2.6 1,134
  32. 32 GLM-5V-Turbo 1,128
  33. 33 GLM-5 1,101
  34. 34 Kimi K2.5 thinking 1,092
  35. 35 GPT-5.5 1,068
  36. 36 Gemini 3 Pro 1,053
  37. 37 Gemini 3.1 Pro 1,046
  38. 38 Gemini 3 Flash 1,042
  39. 39 GPT-5.6 Terra 1,041
  40. 40 Grok 4.20 reasoning 1,033
  41. 41 Claude Sonnet 4.5 1,029
  42. 42 GLM-4.7 1,028
  43. 43 GPT-5.2 1,021
  44. 44 GLM-4.6 1,008
  45. 45 GPT-5.4 996
  46. 46 grok-code-fast-1 988
  47. 47 Grok 4.3 986
  48. 48 GPT-5.2 Codex 972
  49. 49 GPT-5.3 Codex 962

Source: Official DesignArena Full Stack leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 1,393 Sep 2026 Official leaderboard
2 GPT-6 Astra 1,339 xhigh Sep 2026 Official leaderboard
3 Kimi K3.1 Pro 1,328 Oct 2026 Official leaderboard
4 Claude Fable 5.1 1,304 Sep 2026 Official leaderboard
5 Kimi K3 1,295 Jul 2026 Official leaderboard
6 Muse Spark 1.3 1,292 xhigh, max Sep 2026 Official leaderboard
7 Claude Opus 5 1,285 Jul 2026 Official leaderboard
8 Qwen 3.8 Max 1,283 Aug 2026 Official leaderboard
9 Claude Fable 5 1,259 Jun 2026 Official leaderboard
10 Grok 4.6 1,242 Aug 2026 Official leaderboard
11 GPT-5.6 Sol 1,237 medium, xhigh Jul 2026 Official leaderboard
12 Claude Opus 4.8 1,227 May 2026 Official leaderboard
13 Claude Sonnet 5 1,227 Jun 2026 Official leaderboard
14 Grok 4.5 1,227 Jul 2026 Official leaderboard
15 Gemini 3.8 Flash 1,220 Sep 2026 Official leaderboard
16 GLM-5.2 1,219 Jun 2026 Official leaderboard
17 GPT-6 Sol 1,214 Sep 2026 Official leaderboard
18 Claude Opus 4.6 1,199 Feb 2026 Official leaderboard
19 Claude Sonnet 4.6 1,191 Feb 2026 Official leaderboard
20 Muse Spark 1.2 1,188 Aug 2026 Official leaderboard
21 Gemini 3.7 Flash 1,188 Aug 2026 Official leaderboard
22 MiniMax-M3 1,179 Jun 2026 Official leaderboard
23 Gemini 3.5 Flash 1,175 May 2026 Official leaderboard
24 Muse Spark 1.1 1,175 Jul 2026 Official leaderboard
25 Qwen3.7-Max 1,172 May 2026 Official leaderboard
26 Gemini 3.6 Flash 1,159 Jul 2026 Official leaderboard
27 Kimi K2.7 Code 1,154 Jun 2026 Official leaderboard
28 GLM-5.1 1,145 Apr 2026 Official leaderboard
29 GPT-6 Luna 1,140 Sep 2026 Official leaderboard
30 Claude Opus 4.5 1,135 Nov 2025 Official leaderboard
31 Kimi K2.6 1,134 Apr 2026 Official leaderboard
32 GLM-5V-Turbo 1,128 Apr 2026 Official leaderboard
33 GLM-5 1,101 Feb 2026 Official leaderboard
34 Kimi K2.5 1,092 thinking Jan 2026 Official leaderboard
35 GPT-5.5 1,068 Apr 2026 Official leaderboard
36 Gemini 3 Pro 1,053 Nov 2025 Official leaderboard
37 Gemini 3.1 Pro 1,046 Feb 2026 Official leaderboard
38 Gemini 3 Flash 1,042 Dec 2025 Official leaderboard
39 GPT-5.6 Terra 1,041 Jul 2026 Official leaderboard
40 Grok 4.20 1,033 reasoning Feb 2026 Official leaderboard
41 Claude Sonnet 4.5 1,029 Sep 2025 Official leaderboard
42 GLM-4.7 1,028 Dec 2025 Official leaderboard
43 GPT-5.2 1,021 Dec 2025 Official leaderboard
44 GLM-4.6 1,008 Sep 2025 Official leaderboard
45 GPT-5.4 996 Mar 2026 Official leaderboard
46 grok-code-fast-1 988 Aug 2025 Official leaderboard
47 Grok 4.3 986 Apr 2026 Official leaderboard
48 GPT-5.2 Codex 972 Dec 2025 Official leaderboard
49 GPT-5.3 Codex 962 Feb 2026 Official leaderboard

11 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Other labs Anthropic Google DeepMind Moonshot AI OpenAI
Own leaderboard 11 leaders
Claude Opus 5.5 1,393

Source: Official DesignArena Full Stack leaderboard

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
900 1,000 1,100 1,200 1,300 1,400 2026 2027 900 1,000 1,100 1,200 1,300 1,400 2026 2027

Source: Official DesignArena Full Stack leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471