Benchmark Almanac

Dubesor Lichess Puzzle Rating

Gemini 4 Neon 2,455 leads since November 2026
Not in model cards

Models solve sequences of moves in 500 rated Lichess puzzles. The organizer fits a performance rating against puzzle difficulty using only first attempts.

Dubesor ranks 68 language model configurations with at least 100 attempts each. A separate column shows how often a second attempt succeeds.

Made by
Dubesor
Released
October 2026
Kind
Puzzles and chess
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
66
Entries on its own leaderboard, 62 models we track

Gemini 4 Neon leads with 2,455 Gemini 4 Neon leads with 2,455

Best score per entry from the benchmark's own leaderboard, read on November 20th, 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. This view shows only models we track, each at its best.

  1. 1 Gemini 4 Neon Classical 2,455
  2. 2 GPT-6.2 Astra Classical 2,244
  3. 3 Gemini 4 Carbon Classical 2,200
  4. 4 Gemini 4 Argon Classical 2,150
  5. 5 Claude Fable 5.2 Classical 2,114
  6. 6 Gemini 3.7 Flash Classical 2,100
  7. 7 Gemini 3.8 Flash Classical 2,091
  8. 8 Gemini 3.1 Pro Classical 2,060
  9. 9 GPT-6.2 Sol Classical 2,053
  10. 10 Gemini 4 Hydrogen Classical 2,052
  11. 11 Gemini 3.6 Flash Classical 1,963
  12. 12 GPT-6 Astra Classical 1,921
  13. 13 o3 Classical 1,843
  14. 14 hy4-flash Classical 1,791
  15. 15 DeepSeek V4.1 Flash 1017 Classical 1,760
  16. 16 GPT-6.1 Sol Classical 1,736
  17. 17 Grok 4.20 Classical 1,631
  18. 18 Claude Opus 5.5 Classical 1,631
  19. 19 Gemini 3 Flash Classical 1,630
  20. 20 Tencent Hy3 Classical 1,616
  21. 21 DeepSeek V4 Flash 0731 Classical 1,600
  22. 22 Muse Ember Classical 1,582
  23. 23 GPT-6.1 Terra Classical 1,571
  24. 24 MiniMax-M3.1-Flash Classical 1,503
  25. 25 muse-spark-1.3-contributor Classical 1,493
  26. 26 maia5-1500 Classical 1,391
  27. 27 GPT-5.6 Terra Classical 1,384
  28. 28 Claude Sonnet 5.5 Classical 1,325
  29. 29 GPT-5.6 Luna Classical 1,317
  30. 30 Nemotron 3.5 Super VL Classical 1,266
  31. 31 Claude Haiku 5.5 Classical 1,239
  32. 32 gpt-oss-120b Classical 1,183
  33. 33 GPT-6 Luna pro, Classical 1,157
  34. 34 Gemini 3.1 Flash-Lite Classical 1,083
  35. 35 Claude Opus 4.8 Classical 1,083
  36. 36 gpt-oss-20b Classical 1,029
  37. 37 Qwen3.7 Flash Classical 986
  38. 38 Nemotron 3 Ultra Classical 977
  39. 39 Gemini 3.5 Flash-Lite Classical 973
  40. 40 GPT-4.1 Classical 915
  41. 41 Gemma 4 31B IT Classical 863
  42. 42 Gemini 2.5 Pro Jun 2025, Classical 859
  43. 43 GPT-4o Mar 2025, Classical 843
  44. 44 Llama 4 Maverick Classical 843
  45. 45 Gemma 4 26B A4B Classical 833
  46. 46 DeepSeek-V3.2 Classical 790
  47. 47 North Mini Code 1.0 Classical 780
  48. 48 Mistral Large 4 Classical 769
  49. 49 Nemotron 3.5 Lightning 30B-A3B Classical 723
  50. 50 GPT-4 Turbo Apr 2024, Classical 721
  51. 51 Kimi K2 Sep 2025, Classical 709
  52. 52 GPT-5.4 Nano Classical 689
  53. 53 GPT-4.1 mini Classical 675
  54. 54 Gemini 2.5 Flash Sep 2025, Classical 638
  55. 55 Mistral Large 3 Classical 638
  56. 56 GPT-4o mini Classical 614
  57. 57 Llama 3.3 70B Instruct Classical 560
  58. 58 Gemini 2.5 Flash-Lite Sep 2025, Classical 560
  59. 59 Phi-4 Classical 528
  60. 60 DeepSeek-V3 Mar 2025, Classical 528
  61. 61 Solar Pro 4 Classical 504
  62. 62 Gemma 2 27B Classical 492
  63. 63 GPT-3.5 Turbo Jan 2024, Classical 398
  64. 64 Llama 4 Scout Classical 377
  65. 65 ministral-3b-2512 Classical 301
  66. 66 Command R7B Classical 174

Source: Official Dubesor Lichess Puzzle Rating leaderboard

  1. 1 Gemini 4 Neon Classical 2,455
  2. 2 GPT-6.2 Astra Classical 2,244
  3. 3 Gemini 4 Carbon Classical 2,200
  4. 4 Gemini 4 Argon Classical 2,150
  5. 5 Claude Fable 5.2 Classical 2,114
  6. 6 Gemini 3.7 Flash Classical 2,100
  7. 7 Gemini 3.8 Flash Classical 2,091
  8. 8 Gemini 3.1 Pro Classical 2,060
  9. 9 GPT-6.2 Sol Classical 2,053
  10. 10 Gemini 4 Hydrogen Classical 2,052
  11. 11 Gemini 3.6 Flash Classical 1,963
  12. 12 GPT-6 Astra Classical 1,921
  13. 13 o3 Classical 1,843
  14. 14 DeepSeek V4.1 Flash 1017 Classical 1,760
  15. 15 GPT-6.1 Sol Classical 1,736
  16. 16 Grok 4.20 Classical 1,631
  17. 17 Claude Opus 5.5 Classical 1,631
  18. 18 Gemini 3 Flash Classical 1,630
  19. 19 Tencent Hy3 Classical 1,616
  20. 20 DeepSeek V4 Flash 0731 Classical 1,600
  21. 21 Muse Ember Classical 1,582
  22. 22 GPT-6.1 Terra Classical 1,571
  23. 23 MiniMax-M3.1-Flash Classical 1,503
  24. 24 GPT-5.6 Terra Classical 1,384
  25. 25 Claude Sonnet 5.5 Classical 1,325
  26. 26 GPT-5.6 Luna Classical 1,317
  27. 27 Nemotron 3.5 Super VL Classical 1,266
  28. 28 Claude Haiku 5.5 Classical 1,239
  29. 29 gpt-oss-120b Classical 1,183
  30. 30 GPT-6 Luna pro, Classical 1,157
  31. 31 Gemini 3.1 Flash-Lite Classical 1,083
  32. 32 Claude Opus 4.8 Classical 1,083
  33. 33 gpt-oss-20b Classical 1,029
  34. 34 Qwen3.7 Flash Classical 986
  35. 35 Nemotron 3 Ultra Classical 977
  36. 36 Gemini 3.5 Flash-Lite Classical 973
  37. 37 GPT-4.1 Classical 915
  38. 38 Gemma 4 31B IT Classical 863
  39. 39 Gemini 2.5 Pro Jun 2025, Classical 859
  40. 40 GPT-4o Mar 2025, Classical 843
  41. 41 Llama 4 Maverick Classical 843
  42. 42 Gemma 4 26B A4B Classical 833
  43. 43 DeepSeek-V3.2 Classical 790
  44. 44 North Mini Code 1.0 Classical 780
  45. 45 Mistral Large 4 Classical 769
  46. 46 Nemotron 3.5 Lightning 30B-A3B Classical 723
  47. 47 GPT-4 Turbo Apr 2024, Classical 721
  48. 48 Kimi K2 Sep 2025, Classical 709
  49. 49 GPT-5.4 Nano Classical 689
  50. 50 GPT-4.1 mini Classical 675
  51. 51 Gemini 2.5 Flash Sep 2025, Classical 638
  52. 52 Mistral Large 3 Classical 638
  53. 53 GPT-4o mini Classical 614
  54. 54 Llama 3.3 70B Instruct Classical 560
  55. 55 Gemini 2.5 Flash-Lite Sep 2025, Classical 560
  56. 56 Phi-4 Classical 528
  57. 57 DeepSeek-V3 Mar 2025, Classical 528
  58. 58 Solar Pro 4 Classical 504
  59. 59 Gemma 2 27B Classical 492
  60. 60 GPT-3.5 Turbo Jan 2024, Classical 398
  61. 61 Llama 4 Scout Classical 377
  62. 62 Command R7B Classical 174

Source: Official Dubesor Lichess Puzzle Rating leaderboard

#EntryScore ±SettingDateSource
1 Gemini 4 Neon 2,455 ±106 Classical Nov 2026 Official leaderboard
2 GPT-6.2 Astra 2,244 ±77 Classical Nov 2026 Official leaderboard
3 Gemini 4 Carbon 2,200 ±76 Classical Oct 2026 Official leaderboard
4 Gemini 4 Argon 2,150 ±74 Classical Sep 2026 Official leaderboard
5 Claude Fable 5.2 2,114 ±112 Classical Nov 2026 Official leaderboard
6 Gemini 3.7 Flash 2,100 ±54 Classical Aug 2026 Official leaderboard
7 Gemini 3.8 Flash 2,091 ±53 Classical Sep 2026 Official leaderboard
8 Gemini 3.1 Pro 2,060 ±81 Classical Feb 2026 Official leaderboard
9 GPT-6.2 Sol 2,053 ±53 Classical Nov 2026 Official leaderboard
10 Gemini 4 Hydrogen 2,052 ±81 Classical Nov 2026 Official leaderboard
11 Gemini 3.6 Flash 1,963 ±52 Classical Jul 2026 Official leaderboard
12 GPT-6 Astra 1,921 ±71 Classical Sep 2026 Official leaderboard
13 o3 1,843 ±111 Classical Apr 2025 Official leaderboard
14 hy4-flash 1,791 ±51 Classical Official leaderboard
15 DeepSeek V4.1 Flash 1017 1,760 ±81 Classical Oct 2026 Official leaderboard
16 GPT-6.1 Sol 1,736 ±51 Classical Sep 2026 Official leaderboard
17 Grok 4.20 1,631 ±117 Classical Feb 2026 Official leaderboard
18 Claude Opus 5.5 1,631 ±72 Classical Sep 2026 Official leaderboard
19 Gemini 3 Flash 1,630 ±51 Classical Dec 2025 Official leaderboard
20 Tencent Hy3 1,616 ±72 Classical Jul 2026 Official leaderboard
21 DeepSeek V4 Flash 0731 1,600 ±81 Classical Jul 2026 Official leaderboard
22 Muse Ember 1,582 ±102 Classical Nov 2026 Official leaderboard
23 GPT-6.1 Terra 1,571 ±51 Classical Oct 2026 Official leaderboard
24 MiniMax-M3.1-Flash 1,503 ±81 Classical Oct 2026 Official leaderboard
25 muse-spark-1.3-contributor 1,493 ±51 Classical Official leaderboard
26 maia5-1500 1,391 ±51 Classical Official leaderboard
27 GPT-5.6 Terra 1,384 ±81 Classical Jul 2026 Official leaderboard
28 Claude Sonnet 5.5 1,325 ±81 Classical Sep 2026 Official leaderboard
29 GPT-5.6 Luna 1,317 ±51 Classical Jul 2026 Official leaderboard
30 Nemotron 3.5 Super VL 1,266 ±80 Classical Oct 2026 Official leaderboard
31 Claude Haiku 5.5 1,239 ±51 Classical Oct 2026 Official leaderboard
32 gpt-oss-120b 1,183 ±51 Classical Aug 2025 Official leaderboard
33 GPT-6 Luna 1,157 ±82 pro, Classical Sep 2026 Official leaderboard
34 Gemini 3.1 Flash-Lite 1,083 ±52 Classical Mar 2026 Official leaderboard
35 Claude Opus 4.8 1,083 ±119 Classical May 2026 Official leaderboard
36 gpt-oss-20b 1,029 ±53 Classical Aug 2025 Official leaderboard
37 Qwen3.7 Flash 986 ±54 Classical Jul 2026 Official leaderboard
38 Nemotron 3 Ultra 977 ±94 Classical Jun 2026 Official leaderboard
39 Gemini 3.5 Flash-Lite 973 ±54 Classical Jul 2026 Official leaderboard
40 GPT-4.1 915 ±55 Classical Apr 2025 Official leaderboard
41 Gemma 4 31B IT 863 ±57 Classical Apr 2026 Official leaderboard
42 Gemini 2.5 Pro Jun 2025 859 ±129 Classical Jun 2025 Official leaderboard
43 GPT-4o Mar 2025 843 ±58 Classical Mar 2025 Official leaderboard
44 Llama 4 Maverick 843 ±58 Classical Apr 2025 Official leaderboard
45 Gemma 4 26B A4B 833 ±58 Classical Apr 2026 Official leaderboard
46 DeepSeek-V3.2 790 ±114 Classical Dec 2025 Official leaderboard
47 North Mini Code 1.0 780 ±61 Classical Jun 2026 Official leaderboard
48 Mistral Large 4 769 ±130 Classical Oct 2026 Official leaderboard
49 Nemotron 3.5 Lightning 30B-A3B 723 ±75 Classical Aug 2026 Official leaderboard
50 GPT-4 Turbo Apr 2024 721 ±65 Classical Apr 2024 Official leaderboard
51 Kimi K2 Sep 2025 709 ±66 Classical Sep 2025 Official leaderboard
52 GPT-5.4 Nano 689 ±67 Classical Mar 2026 Official leaderboard
53 GPT-4.1 mini 675 ±68 Classical Apr 2025 Official leaderboard
54 Gemini 2.5 Flash Sep 2025 638 ±72 Classical Sep 2025 Official leaderboard
55 Mistral Large 3 638 ±72 Classical Dec 2025 Official leaderboard
56 GPT-4o mini 614 ±75 Classical Jul 2024 Official leaderboard
57 Llama 3.3 70B Instruct 560 ±82 Classical Dec 2024 Official leaderboard
58 Gemini 2.5 Flash-Lite Sep 2025 560 ±82 Classical Sep 2025 Official leaderboard
59 Phi-4 528 ±87 Classical Dec 2024 Official leaderboard
60 DeepSeek-V3 Mar 2025 528 ±87 Classical Mar 2025 Official leaderboard
61 Solar Pro 4 504 ±91 Classical Aug 2026 Official leaderboard
62 Gemma 2 27B 492 ±93 Classical Jun 2024 Official leaderboard
63 GPT-3.5 Turbo Jan 2024 398 ±114 Classical Jan 2024 Official leaderboard
64 Llama 4 Scout 377 ±119 Classical Apr 2025 Official leaderboard
65 ministral-3b-2512 301 ±144 Classical Official leaderboard
66 Command R7B 174 ±200 Classical Dec 2024 Official leaderboard
#ModelScore ±SettingDateSource
1 Gemini 4 Neon 2,455 ±106 Classical Nov 2026 Official leaderboard
2 GPT-6.2 Astra 2,244 ±77 Classical Nov 2026 Official leaderboard
3 Gemini 4 Carbon 2,200 ±76 Classical Oct 2026 Official leaderboard
4 Gemini 4 Argon 2,150 ±74 Classical Sep 2026 Official leaderboard
5 Claude Fable 5.2 2,114 ±112 Classical Nov 2026 Official leaderboard
6 Gemini 3.7 Flash 2,100 ±54 Classical Aug 2026 Official leaderboard
7 Gemini 3.8 Flash 2,091 ±53 Classical Sep 2026 Official leaderboard
8 Gemini 3.1 Pro 2,060 ±81 Classical Feb 2026 Official leaderboard
9 GPT-6.2 Sol 2,053 ±53 Classical Nov 2026 Official leaderboard
10 Gemini 4 Hydrogen 2,052 ±81 Classical Nov 2026 Official leaderboard
11 Gemini 3.6 Flash 1,963 ±52 Classical Jul 2026 Official leaderboard
12 GPT-6 Astra 1,921 ±71 Classical Sep 2026 Official leaderboard
13 o3 1,843 ±111 Classical Apr 2025 Official leaderboard
14 DeepSeek V4.1 Flash 1017 1,760 ±81 Classical Oct 2026 Official leaderboard
15 GPT-6.1 Sol 1,736 ±51 Classical Sep 2026 Official leaderboard
16 Grok 4.20 1,631 ±117 Classical Feb 2026 Official leaderboard
17 Claude Opus 5.5 1,631 ±72 Classical Sep 2026 Official leaderboard
18 Gemini 3 Flash 1,630 ±51 Classical Dec 2025 Official leaderboard
19 Tencent Hy3 1,616 ±72 Classical Jul 2026 Official leaderboard
20 DeepSeek V4 Flash 0731 1,600 ±81 Classical Jul 2026 Official leaderboard
21 Muse Ember 1,582 ±102 Classical Nov 2026 Official leaderboard
22 GPT-6.1 Terra 1,571 ±51 Classical Oct 2026 Official leaderboard
23 MiniMax-M3.1-Flash 1,503 ±81 Classical Oct 2026 Official leaderboard
24 GPT-5.6 Terra 1,384 ±81 Classical Jul 2026 Official leaderboard
25 Claude Sonnet 5.5 1,325 ±81 Classical Sep 2026 Official leaderboard
26 GPT-5.6 Luna 1,317 ±51 Classical Jul 2026 Official leaderboard
27 Nemotron 3.5 Super VL 1,266 ±80 Classical Oct 2026 Official leaderboard
28 Claude Haiku 5.5 1,239 ±51 Classical Oct 2026 Official leaderboard
29 gpt-oss-120b 1,183 ±51 Classical Aug 2025 Official leaderboard
30 GPT-6 Luna 1,157 ±82 pro, Classical Sep 2026 Official leaderboard
31 Gemini 3.1 Flash-Lite 1,083 ±52 Classical Mar 2026 Official leaderboard
32 Claude Opus 4.8 1,083 ±119 Classical May 2026 Official leaderboard
33 gpt-oss-20b 1,029 ±53 Classical Aug 2025 Official leaderboard
34 Qwen3.7 Flash 986 ±54 Classical Jul 2026 Official leaderboard
35 Nemotron 3 Ultra 977 ±94 Classical Jun 2026 Official leaderboard
36 Gemini 3.5 Flash-Lite 973 ±54 Classical Jul 2026 Official leaderboard
37 GPT-4.1 915 ±55 Classical Apr 2025 Official leaderboard
38 Gemma 4 31B IT 863 ±57 Classical Apr 2026 Official leaderboard
39 Gemini 2.5 Pro Jun 2025 859 ±129 Classical Jun 2025 Official leaderboard
40 GPT-4o Mar 2025 843 ±58 Classical Mar 2025 Official leaderboard
41 Llama 4 Maverick 843 ±58 Classical Apr 2025 Official leaderboard
42 Gemma 4 26B A4B 833 ±58 Classical Apr 2026 Official leaderboard
43 DeepSeek-V3.2 790 ±114 Classical Dec 2025 Official leaderboard
44 North Mini Code 1.0 780 ±61 Classical Jun 2026 Official leaderboard
45 Mistral Large 4 769 ±130 Classical Oct 2026 Official leaderboard
46 Nemotron 3.5 Lightning 30B-A3B 723 ±75 Classical Aug 2026 Official leaderboard
47 GPT-4 Turbo Apr 2024 721 ±65 Classical Apr 2024 Official leaderboard
48 Kimi K2 Sep 2025 709 ±66 Classical Sep 2025 Official leaderboard
49 GPT-5.4 Nano 689 ±67 Classical Mar 2026 Official leaderboard
50 GPT-4.1 mini 675 ±68 Classical Apr 2025 Official leaderboard
51 Gemini 2.5 Flash Sep 2025 638 ±72 Classical Sep 2025 Official leaderboard
52 Mistral Large 3 638 ±72 Classical Dec 2025 Official leaderboard
53 GPT-4o mini 614 ±75 Classical Jul 2024 Official leaderboard
54 Llama 3.3 70B Instruct 560 ±82 Classical Dec 2024 Official leaderboard
55 Gemini 2.5 Flash-Lite Sep 2025 560 ±82 Classical Sep 2025 Official leaderboard
56 Phi-4 528 ±87 Classical Dec 2024 Official leaderboard
57 DeepSeek-V3 Mar 2025 528 ±87 Classical Mar 2025 Official leaderboard
58 Solar Pro 4 504 ±91 Classical Aug 2026 Official leaderboard
59 Gemma 2 27B 492 ±93 Classical Jun 2024 Official leaderboard
60 GPT-3.5 Turbo Jan 2024 398 ±114 Classical Jan 2024 Official leaderboard
61 Llama 4 Scout 377 ±119 Classical Apr 2025 Official leaderboard
62 Command R7B 174 ±200 Classical Dec 2024 Official leaderboard

Rankings by part

We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 573 to 799, 802 to 992 and 1000 to 1199. Gemini 4 Neon leads 6 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

573 to 799

62 models we track have a score here.

  1. 1 o3 ↑12 100%
  2. 2 Grok 4.20 ↑14 100%
  3. 3 GPT-6 Astra ↑9 100%
  4. 4 Gemini 4 Argon 100%
  5. 5 DeepSeek V4.1 Flash 1017 ↑9 100%
  6. 6 Gemini 4 Carbon ↓3 100%
  7. 7 Claude Fable 5.2 ↓2 100%
  8. 8 GPT-6.2 Astra ↓6 100%
  9. 9 GPT-6.2 Sol 100%
  10. 10 Gemini 4 Neon ↓9 100%

The best score, 2,455, costs $0.16 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Cohere Microsoft Google DeepMind Cost frontier One model at each effort level
0 500 1,000 1,500 2,000 2,500 $0.00001 $0.0001 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, Classical GPT-6.2 Astra, Classical Gemini 3.7 Flash, Classical Gemini 3 Flash, Classical Gemini 3.1 Flash-Lite, Classical GPT-4o mini, Classical Command R7B, Classical 0 500 1,000 1,500 2,000 2,500 $0.00001 $0.0001 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, Classical GPT-6.2 Astra, Classical

Source: Official Dubesor Lichess Puzzle Rating leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Neon Classical 2,455 $0.16
Gemini 4 Neon Rapid 2,252 $0.16
GPT-6.2 Astra Classical 2,244 $0.05
GPT-6.2 Astra Rapid 2,244 $0.05
GPT-6.2 Astra Blitz 2,244 $0.05
GPT-6.2 Astra Bullet 2,209 $0.05
Gemini 4 Carbon Classical 2,200 $0.08
Gemini 4 Carbon Rapid 2,200 $0.08
Gemini 4 Argon Classical 2,150 $0.07
Gemini 4 Argon Rapid 2,150 $0.07
Claude Fable 5.2 Classical 2,114 $0.33
Claude Fable 5.2 Rapid 2,114 $0.33
Gemini 3.7 Flash Classical 2,100 $0.01
Gemini 3.7 Flash Rapid 2,100 $0.01
Gemini 3.7 Flash Blitz 2,096 $0.01
Gemini 3.8 Flash Classical 2,091 $0.01
Gemini 3.8 Flash Rapid 2,091 $0.01
Claude Fable 5.2 Blitz 2,077 $0.33
Gemini 3.8 Flash Blitz 2,070 $0.01
Gemini 3.1 Pro Classical 2,060 $0.35
GPT-6.2 Sol Classical 2,053 $0.03
GPT-6.2 Sol Rapid 2,053 $0.03
GPT-6.2 Sol Blitz 2,053 $0.03
Gemini 4 Hydrogen Classical 2,052 $0.10
Gemini 4 Argon Blitz 2,037 $0.07
Gemini 4 Carbon Blitz 1,990 $0.08
Gemini 3.6 Flash Classical 1,963 $0.02
Gemini 3.6 Flash Rapid 1,963 $0.02
Gemini 3.6 Flash Blitz 1,951 $0.02
Gemini 4 Hydrogen Rapid 1,937 $0.10
Gemini 3.1 Pro Rapid 1,934 $0.35
GPT-6 Astra Classical 1,921 $0.09
GPT-6 Astra Rapid 1,921 $0.09
GPT-6 Astra Blitz 1,921 $0.09
o3 Classical 1,843 $0.26
Gemini 4 Argon Classical 1,843 $0.01
Gemini 4 Argon Rapid 1,843 $0.01
Gemini 4 Argon Blitz 1,843 $0.01
Gemini 4 Argon Bullet 1,815 $0.01
o3 Rapid 1,769 $0.26
GPT-6.2 Sol Bullet 1,768 $0.03
DeepSeek V4.1 Flash 1017 Classical 1,760 $0.07
GPT-6.1 Sol Classical 1,736 $0.02
GPT-6.1 Sol Rapid 1,736 $0.02
GPT-6.1 Sol Blitz 1,736 $0.02
Gemini 4 Neon Blitz 1,664 $0.16
Grok 4.20 Classical 1,631 $0.10
Claude Opus 5.5 Classical 1,631 $0.07
Claude Opus 5.5 Rapid 1,631 $0.07
Claude Opus 5.5 Blitz 1,631 $0.07
Gemini 3 Flash Classical 1,630 $0.001
Gemini 3 Flash Rapid 1,630 $0.001
Gemini 3 Flash Blitz 1,630 $0.001
Gemini 3 Flash Bullet 1,630 $0.001
Tencent Hy3 Classical 1,616 $0.03
DeepSeek V4 Flash 0731 Classical 1,600 $0.04
Claude Fable 5.2 Bullet 1,589 $0.33
Muse Ember Classical 1,582 $0.08
GPT-6.1 Terra Classical 1,571 $0.01
GPT-6.1 Terra Rapid 1,571 $0.01
GPT-6.1 Terra Blitz 1,571 $0.01
Gemini 3.7 Flash Bullet 1,552 $0.01
Gemini 4 Hydrogen Blitz 1,531 $0.10
Grok 4.20 Rapid 1,506 $0.10
MiniMax-M3.1-Flash Classical 1,503 $0.13
Gemini 3.8 Flash Bullet 1,481 $0.01
GPT-6 Astra Bullet 1,475 $0.09
GPT-6.1 Sol Bullet 1,469 $0.02
GPT-5.6 Terra Classical 1,384 $0.03
GPT-5.6 Terra Rapid 1,384 $0.03
GPT-5.6 Terra Blitz 1,374 $0.03
Tencent Hy3 Rapid 1,356 $0.03
Claude Opus 5.5 Bullet 1,332 $0.07
Claude Sonnet 5.5 Classical 1,325 $0.04
Claude Sonnet 5.5 Rapid 1,325 $0.04
Claude Sonnet 5.5 Blitz 1,325 $0.04
GPT-5.6 Luna Classical 1,317 $0.005
GPT-5.6 Luna Rapid 1,317 $0.005
Gemini 4 Carbon Bullet 1,300 $0.08
GPT-5.6 Luna Blitz 1,270 $0.005
Nemotron 3.5 Super VL Classical 1,266 $0.09
Claude Haiku 5.5 Classical 1,239 $0.003
Claude Haiku 5.5 Rapid 1,239 $0.003
Claude Haiku 5.5 Blitz 1,223 $0.003
gpt-oss-120b Classical 1,183 $0.004
gpt-oss-120b Rapid 1,180 $0.004
GPT-6.1 Terra Bullet 1,168 $0.01
GPT-6 Luna pro, Classical 1,157 $0.01
GPT-6 Luna pro, Rapid 1,157 $0.01
Muse Ember Rapid 1,132 $0.08
DeepSeek V4.1 Flash 1017 Rapid 1,127 $0.07
GPT-6 Luna Classical 1,103 $0.004
GPT-6 Luna Rapid 1,103 $0.004
MiniMax-M3.1-Flash Rapid 1,096 $0.13
Gemini 3.1 Flash-Lite Classical 1,083 $0.0005
Gemini 3.1 Flash-Lite Rapid 1,083 $0.0005
Gemini 3.1 Flash-Lite Blitz 1,083 $0.0005
Gemini 3.1 Flash-Lite Bullet 1,083 $0.0005
Claude Opus 4.8 Classical 1,083 $0.06
Claude Opus 4.8 Rapid 1,083 $0.06
Claude Opus 4.8 Blitz 1,083 $0.06
GPT-6 Luna Blitz 1,058 $0.004
Claude Sonnet 5.5 Bullet 1,055 $0.04
Gemini 3.1 Pro Blitz 1,045 $0.35
GPT-5.6 Terra Bullet 1,045 $0.03
gpt-oss-20b Classical 1,029 $0.01
Claude Opus 4.8 Bullet 1,019 $0.06
Gemini 4 Argon Bullet 1,002 $0.07
Qwen3.7 Flash Classical 986 $0.007
Nemotron 3 Ultra Classical 977
Gemini 3.5 Flash-Lite Classical 973 $0.001
Gemini 3.5 Flash-Lite Rapid 973 $0.001
Gemini 3.5 Flash-Lite Blitz 973 $0.001
Gemini 3.5 Flash-Lite Bullet 973 $0.001
DeepSeek V4 Flash 0731 Rapid 961 $0.04
GPT-4.1 Classical 915 $0.004
GPT-4.1 Rapid 915 $0.004
GPT-4.1 Blitz 915 $0.004
GPT-4.1 Bullet 915 $0.004
Gemini 3.6 Flash Bullet 910 $0.02
gpt-oss-20b Rapid 877 $0.01
Gemma 4 31B IT Classical 863 $0.002
Gemma 4 31B IT Rapid 863 $0.002
Gemma 4 31B IT Blitz 863 $0.002
Gemini 2.5 Pro Jun 2025 Classical 859 $0.16
Gemma 4 31B IT Bullet 853 $0.002
GPT-4o Mar 2025 Classical 843 $0.005
GPT-4o Mar 2025 Rapid 843 $0.005
GPT-4o Mar 2025 Blitz 843 $0.005
GPT-4o Mar 2025 Bullet 843 $0.005
Llama 4 Maverick Classical 843 $0.001
Llama 4 Maverick Rapid 843 $0.001
Llama 4 Maverick Blitz 843 $0.001
Llama 4 Maverick Bullet 838 $0.001
Gemini 2.5 Pro Jun 2025 Rapid 834 $0.16
Gemma 4 26B A4B Classical 833
Gemma 4 26B A4B Rapid 833
Gemma 4 26B A4B Blitz 823
Nemotron 3.5 Super VL Rapid 792 $0.09
DeepSeek-V3.2 Classical 790 $0.009
North Mini Code 1.0 Classical 780
Mistral Large 4 Classical 769 $0.04
Qwen3.7 Flash Rapid 763 $0.007
gpt-oss-120b Blitz 757 $0.004
Gemma 4 26B A4B Bullet 757
GPT-6 Luna pro, Blitz 743 $0.01
MiniMax-M3.1-Flash Blitz 727 $0.13
Nemotron 3.5 Lightning 30B-A3B Classical 723 $0.003
GPT-4 Turbo Apr 2024 Classical 721 $0.03
GPT-4 Turbo Apr 2024 Rapid 721 $0.03
GPT-4 Turbo Apr 2024 Blitz 721 $0.03
GPT-4 Turbo Apr 2024 Bullet 721 $0.03
Mistral Large 4 Rapid 715 $0.04
Kimi K2 Sep 2025 Classical 709 $0.004
Kimi K2 Sep 2025 Rapid 709 $0.004
Kimi K2 Sep 2025 Blitz 709 $0.004
Grok 4.20 Classical 702 $0.004
Grok 4.20 Rapid 702 $0.004
Grok 4.20 Blitz 689 $0.004
GPT-5.4 Nano Classical 689 $0.0006
GPT-5.4 Nano Rapid 689 $0.0006
GPT-5.4 Nano Blitz 689 $0.0006
GPT-5.4 Nano Bullet 689 $0.0006
Kimi K2 Sep 2025 Bullet 682 $0.004
DeepSeek-V3.2 Rapid 681 $0.009
GPT-4.1 mini Classical 675 $0.0007
GPT-4.1 mini Rapid 675 $0.0007
GPT-4.1 mini Blitz 675 $0.0007
GPT-4.1 mini Bullet 675 $0.0007
Nemotron 3 Ultra Rapid 667
Gemini 2.5 Pro Jun 2025 Blitz 644 $0.16
Gemini 2.5 Flash Sep 2025 Classical 638 $0.01
Gemini 2.5 Flash Sep 2025 Rapid 638 $0.01
Gemini 2.5 Flash Sep 2025 Blitz 638 $0.01
Mistral Large 3 Classical 638 $0.0009
Mistral Large 3 Rapid 638 $0.0009
Mistral Large 3 Blitz 638 $0.0009
Mistral Large 3 Bullet 638 $0.0009
GPT-6 Luna Bullet 631 $0.004
Mistral Large 4 Blitz 615 $0.04
GPT-4o mini Classical 614 $0.0002
GPT-4o mini Rapid 614 $0.0002
GPT-4o mini Blitz 614 $0.0002
GPT-4o mini Bullet 614 $0.0002
Grok 4.20 Bullet 606 $0.004
Gemini 2.5 Flash Sep 2025 Bullet 588 $0.01
DeepSeek V4.1 Flash 1017 Blitz 572 $0.07
Llama 3.3 70B Instruct Classical 560 $0.0004
Llama 3.3 70B Instruct Rapid 560 $0.0004
Llama 3.3 70B Instruct Blitz 560 $0.0004
Llama 3.3 70B Instruct Bullet 560 $0.0004
Gemini 2.5 Flash-Lite Sep 2025 Classical 560 $0.004
Gemini 2.5 Flash-Lite Sep 2025 Rapid 550 $0.004
Gemini 4 Hydrogen Bullet 546 $0.10
Gemini 2.5 Flash-Lite Sep 2025 Blitz 539 $0.004
Phi-4 Classical 528 $0.0001
Phi-4 Rapid 528 $0.0001
Phi-4 Blitz 528 $0.0001
Phi-4 Bullet 528 $0.0001
DeepSeek-V3 Mar 2025 Classical 528 $0.0006
DeepSeek-V3 Mar 2025 Rapid 528 $0.0006
DeepSeek-V3 Mar 2025 Blitz 528 $0.0006
DeepSeek-V3 Mar 2025 Bullet 528 $0.0006
GPT-5.6 Luna Bullet 516 $0.005
Solar Pro 4 Classical 504 $0.002
Gemma 2 27B Classical 492 $0.0005
Gemma 2 27B Rapid 492 $0.0005
Gemma 2 27B Blitz 492 $0.0005
Gemma 2 27B Bullet 492 $0.0005
Solar Pro 4 Rapid 492 $0.002
Solar Pro 4 Blitz 479 $0.002
Solar Pro 4 Bullet 479 $0.002
Claude Haiku 5.5 Bullet 465 $0.003
North Mini Code 1.0 Rapid 434
Qwen3.7 Flash Blitz 416 $0.007
GPT-3.5 Turbo Jan 2024 Classical 398 $0.0005
GPT-3.5 Turbo Jan 2024 Rapid 398 $0.0005
GPT-3.5 Turbo Jan 2024 Blitz 398 $0.0005
GPT-3.5 Turbo Jan 2024 Bullet 398 $0.0005
Llama 4 Scout Classical 377 $0.0002
Llama 4 Scout Rapid 377 $0.0002
Llama 4 Scout Blitz 377 $0.0002
Llama 4 Scout Bullet 377 $0.0002
Gemini 2.5 Flash-Lite Sep 2025 Bullet 377 $0.004
Command R7B Classical 174 $0.00005

The best score, 2,455, costs $0.16 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Cohere Microsoft Google DeepMind Cost frontier One model at each effort level
0 500 1,000 1,500 2,000 2,500 $0.00001 $0.0001 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, Classical GPT-6.2 Astra, Classical Gemini 3.7 Flash, Classical Gemini 3 Flash, Classical Gemini 3.1 Flash-Lite, Classical GPT-4o mini, Classical Command R7B, Classical 0 500 1,000 1,500 2,000 2,500 $0.00001 $0.0001 $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, Classical GPT-6.2 Astra, Classical

Source: Official Dubesor Lichess Puzzle Rating leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Neon Classical 2,455 $0.16
Gemini 4 Neon Rapid 2,252 $0.16
GPT-6.2 Astra Classical 2,244 $0.05
GPT-6.2 Astra Rapid 2,244 $0.05
GPT-6.2 Astra Blitz 2,244 $0.05
GPT-6.2 Astra Bullet 2,209 $0.05
Gemini 4 Carbon Classical 2,200 $0.08
Gemini 4 Carbon Rapid 2,200 $0.08
Gemini 4 Argon Classical 2,150 $0.07
Gemini 4 Argon Rapid 2,150 $0.07
Claude Fable 5.2 Classical 2,114 $0.33
Claude Fable 5.2 Rapid 2,114 $0.33
Gemini 3.7 Flash Classical 2,100 $0.01
Gemini 3.7 Flash Rapid 2,100 $0.01
Gemini 3.7 Flash Blitz 2,096 $0.01
Gemini 3.8 Flash Classical 2,091 $0.01
Gemini 3.8 Flash Rapid 2,091 $0.01
Claude Fable 5.2 Blitz 2,077 $0.33
Gemini 3.8 Flash Blitz 2,070 $0.01
Gemini 3.1 Pro Classical 2,060 $0.35
GPT-6.2 Sol Classical 2,053 $0.03
GPT-6.2 Sol Rapid 2,053 $0.03
GPT-6.2 Sol Blitz 2,053 $0.03
Gemini 4 Hydrogen Classical 2,052 $0.10
Gemini 4 Argon Blitz 2,037 $0.07
Gemini 4 Carbon Blitz 1,990 $0.08
Gemini 3.6 Flash Classical 1,963 $0.02
Gemini 3.6 Flash Rapid 1,963 $0.02
Gemini 3.6 Flash Blitz 1,951 $0.02
Gemini 4 Hydrogen Rapid 1,937 $0.10
Gemini 3.1 Pro Rapid 1,934 $0.35
GPT-6 Astra Classical 1,921 $0.09
GPT-6 Astra Rapid 1,921 $0.09
GPT-6 Astra Blitz 1,921 $0.09
o3 Classical 1,843 $0.26
Gemini 4 Argon Classical 1,843 $0.01
Gemini 4 Argon Rapid 1,843 $0.01
Gemini 4 Argon Blitz 1,843 $0.01
Gemini 4 Argon Bullet 1,815 $0.01
o3 Rapid 1,769 $0.26
GPT-6.2 Sol Bullet 1,768 $0.03
DeepSeek V4.1 Flash 1017 Classical 1,760 $0.07
GPT-6.1 Sol Classical 1,736 $0.02
GPT-6.1 Sol Rapid 1,736 $0.02
GPT-6.1 Sol Blitz 1,736 $0.02
Gemini 4 Neon Blitz 1,664 $0.16
Grok 4.20 Classical 1,631 $0.10
Claude Opus 5.5 Classical 1,631 $0.07
Claude Opus 5.5 Rapid 1,631 $0.07
Claude Opus 5.5 Blitz 1,631 $0.07
Gemini 3 Flash Classical 1,630 $0.001
Gemini 3 Flash Rapid 1,630 $0.001
Gemini 3 Flash Blitz 1,630 $0.001
Gemini 3 Flash Bullet 1,630 $0.001
Tencent Hy3 Classical 1,616 $0.03
DeepSeek V4 Flash 0731 Classical 1,600 $0.04
Claude Fable 5.2 Bullet 1,589 $0.33
Muse Ember Classical 1,582 $0.08
GPT-6.1 Terra Classical 1,571 $0.01
GPT-6.1 Terra Rapid 1,571 $0.01
GPT-6.1 Terra Blitz 1,571 $0.01
Gemini 3.7 Flash Bullet 1,552 $0.01
Gemini 4 Hydrogen Blitz 1,531 $0.10
Grok 4.20 Rapid 1,506 $0.10
MiniMax-M3.1-Flash Classical 1,503 $0.13
Gemini 3.8 Flash Bullet 1,481 $0.01
GPT-6 Astra Bullet 1,475 $0.09
GPT-6.1 Sol Bullet 1,469 $0.02
GPT-5.6 Terra Classical 1,384 $0.03
GPT-5.6 Terra Rapid 1,384 $0.03
GPT-5.6 Terra Blitz 1,374 $0.03
Tencent Hy3 Rapid 1,356 $0.03
Claude Opus 5.5 Bullet 1,332 $0.07
Claude Sonnet 5.5 Classical 1,325 $0.04
Claude Sonnet 5.5 Rapid 1,325 $0.04
Claude Sonnet 5.5 Blitz 1,325 $0.04
GPT-5.6 Luna Classical 1,317 $0.005
GPT-5.6 Luna Rapid 1,317 $0.005
Gemini 4 Carbon Bullet 1,300 $0.08
GPT-5.6 Luna Blitz 1,270 $0.005
Nemotron 3.5 Super VL Classical 1,266 $0.09
Claude Haiku 5.5 Classical 1,239 $0.003
Claude Haiku 5.5 Rapid 1,239 $0.003
Claude Haiku 5.5 Blitz 1,223 $0.003
gpt-oss-120b Classical 1,183 $0.004
gpt-oss-120b Rapid 1,180 $0.004
GPT-6.1 Terra Bullet 1,168 $0.01
GPT-6 Luna pro, Classical 1,157 $0.01
GPT-6 Luna pro, Rapid 1,157 $0.01
Muse Ember Rapid 1,132 $0.08
DeepSeek V4.1 Flash 1017 Rapid 1,127 $0.07
GPT-6 Luna Classical 1,103 $0.004
GPT-6 Luna Rapid 1,103 $0.004
MiniMax-M3.1-Flash Rapid 1,096 $0.13
Gemini 3.1 Flash-Lite Classical 1,083 $0.0005
Gemini 3.1 Flash-Lite Rapid 1,083 $0.0005
Gemini 3.1 Flash-Lite Blitz 1,083 $0.0005
Gemini 3.1 Flash-Lite Bullet 1,083 $0.0005
Claude Opus 4.8 Classical 1,083 $0.06
Claude Opus 4.8 Rapid 1,083 $0.06
Claude Opus 4.8 Blitz 1,083 $0.06
GPT-6 Luna Blitz 1,058 $0.004
Claude Sonnet 5.5 Bullet 1,055 $0.04
Gemini 3.1 Pro Blitz 1,045 $0.35
GPT-5.6 Terra Bullet 1,045 $0.03
gpt-oss-20b Classical 1,029 $0.01
Claude Opus 4.8 Bullet 1,019 $0.06
Gemini 4 Argon Bullet 1,002 $0.07
Qwen3.7 Flash Classical 986 $0.007
Nemotron 3 Ultra Classical 977
Gemini 3.5 Flash-Lite Classical 973 $0.001
Gemini 3.5 Flash-Lite Rapid 973 $0.001
Gemini 3.5 Flash-Lite Blitz 973 $0.001
Gemini 3.5 Flash-Lite Bullet 973 $0.001
DeepSeek V4 Flash 0731 Rapid 961 $0.04
GPT-4.1 Classical 915 $0.004
GPT-4.1 Rapid 915 $0.004
GPT-4.1 Blitz 915 $0.004
GPT-4.1 Bullet 915 $0.004
Gemini 3.6 Flash Bullet 910 $0.02
gpt-oss-20b Rapid 877 $0.01
Gemma 4 31B IT Classical 863 $0.002
Gemma 4 31B IT Rapid 863 $0.002
Gemma 4 31B IT Blitz 863 $0.002
Gemini 2.5 Pro Jun 2025 Classical 859 $0.16
Gemma 4 31B IT Bullet 853 $0.002
GPT-4o Mar 2025 Classical 843 $0.005
GPT-4o Mar 2025 Rapid 843 $0.005
GPT-4o Mar 2025 Blitz 843 $0.005
GPT-4o Mar 2025 Bullet 843 $0.005
Llama 4 Maverick Classical 843 $0.001
Llama 4 Maverick Rapid 843 $0.001
Llama 4 Maverick Blitz 843 $0.001
Llama 4 Maverick Bullet 838 $0.001
Gemini 2.5 Pro Jun 2025 Rapid 834 $0.16
Gemma 4 26B A4B Classical 833
Gemma 4 26B A4B Rapid 833
Gemma 4 26B A4B Blitz 823
Nemotron 3.5 Super VL Rapid 792 $0.09
DeepSeek-V3.2 Classical 790 $0.009
North Mini Code 1.0 Classical 780
Mistral Large 4 Classical 769 $0.04
Qwen3.7 Flash Rapid 763 $0.007
gpt-oss-120b Blitz 757 $0.004
Gemma 4 26B A4B Bullet 757
GPT-6 Luna pro, Blitz 743 $0.01
MiniMax-M3.1-Flash Blitz 727 $0.13
Nemotron 3.5 Lightning 30B-A3B Classical 723 $0.003
GPT-4 Turbo Apr 2024 Classical 721 $0.03
GPT-4 Turbo Apr 2024 Rapid 721 $0.03
GPT-4 Turbo Apr 2024 Blitz 721 $0.03
GPT-4 Turbo Apr 2024 Bullet 721 $0.03
Mistral Large 4 Rapid 715 $0.04
Kimi K2 Sep 2025 Classical 709 $0.004
Kimi K2 Sep 2025 Rapid 709 $0.004
Kimi K2 Sep 2025 Blitz 709 $0.004
Grok 4.20 Classical 702 $0.004
Grok 4.20 Rapid 702 $0.004
Grok 4.20 Blitz 689 $0.004
GPT-5.4 Nano Classical 689 $0.0006
GPT-5.4 Nano Rapid 689 $0.0006
GPT-5.4 Nano Blitz 689 $0.0006
GPT-5.4 Nano Bullet 689 $0.0006
Kimi K2 Sep 2025 Bullet 682 $0.004
DeepSeek-V3.2 Rapid 681 $0.009
GPT-4.1 mini Classical 675 $0.0007
GPT-4.1 mini Rapid 675 $0.0007
GPT-4.1 mini Blitz 675 $0.0007
GPT-4.1 mini Bullet 675 $0.0007
Nemotron 3 Ultra Rapid 667
Gemini 2.5 Pro Jun 2025 Blitz 644 $0.16
Gemini 2.5 Flash Sep 2025 Classical 638 $0.01
Gemini 2.5 Flash Sep 2025 Rapid 638 $0.01
Gemini 2.5 Flash Sep 2025 Blitz 638 $0.01
Mistral Large 3 Classical 638 $0.0009
Mistral Large 3 Rapid 638 $0.0009
Mistral Large 3 Blitz 638 $0.0009
Mistral Large 3 Bullet 638 $0.0009
GPT-6 Luna Bullet 631 $0.004
Mistral Large 4 Blitz 615 $0.04
GPT-4o mini Classical 614 $0.0002
GPT-4o mini Rapid 614 $0.0002
GPT-4o mini Blitz 614 $0.0002
GPT-4o mini Bullet 614 $0.0002
Grok 4.20 Bullet 606 $0.004
Gemini 2.5 Flash Sep 2025 Bullet 588 $0.01
DeepSeek V4.1 Flash 1017 Blitz 572 $0.07
Llama 3.3 70B Instruct Classical 560 $0.0004
Llama 3.3 70B Instruct Rapid 560 $0.0004
Llama 3.3 70B Instruct Blitz 560 $0.0004
Llama 3.3 70B Instruct Bullet 560 $0.0004
Gemini 2.5 Flash-Lite Sep 2025 Classical 560 $0.004
Gemini 2.5 Flash-Lite Sep 2025 Rapid 550 $0.004
Gemini 4 Hydrogen Bullet 546 $0.10
Gemini 2.5 Flash-Lite Sep 2025 Blitz 539 $0.004
Phi-4 Classical 528 $0.0001
Phi-4 Rapid 528 $0.0001
Phi-4 Blitz 528 $0.0001
Phi-4 Bullet 528 $0.0001
DeepSeek-V3 Mar 2025 Classical 528 $0.0006
DeepSeek-V3 Mar 2025 Rapid 528 $0.0006
DeepSeek-V3 Mar 2025 Blitz 528 $0.0006
DeepSeek-V3 Mar 2025 Bullet 528 $0.0006
GPT-5.6 Luna Bullet 516 $0.005
Solar Pro 4 Classical 504 $0.002
Gemma 2 27B Classical 492 $0.0005
Gemma 2 27B Rapid 492 $0.0005
Gemma 2 27B Blitz 492 $0.0005
Gemma 2 27B Bullet 492 $0.0005
Solar Pro 4 Rapid 492 $0.002
Solar Pro 4 Blitz 479 $0.002
Solar Pro 4 Bullet 479 $0.002
Claude Haiku 5.5 Bullet 465 $0.003
North Mini Code 1.0 Rapid 434
Qwen3.7 Flash Blitz 416 $0.007
GPT-3.5 Turbo Jan 2024 Classical 398 $0.0005
GPT-3.5 Turbo Jan 2024 Rapid 398 $0.0005
GPT-3.5 Turbo Jan 2024 Blitz 398 $0.0005
GPT-3.5 Turbo Jan 2024 Bullet 398 $0.0005
Llama 4 Scout Classical 377 $0.0002
Llama 4 Scout Rapid 377 $0.0002
Llama 4 Scout Blitz 377 $0.0002
Llama 4 Scout Bullet 377 $0.0002
Gemini 2.5 Flash-Lite Sep 2025 Bullet 377 $0.004
Command R7B Classical 174 $0.00005

4 models have held number one on the official leaderboard since its release in October 2026

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

Google DeepMind OpenAI
Own leaderboard 4 leaders

Source: Official Dubesor Lichess Puzzle Rating leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard
0 500 1,000 1,500 2,000 2,500 2024 2025 2026 2027 0 500 1,000 1,500 2,000 2,500 2024 2025 2026 2027

Source: Official Dubesor Lichess Puzzle Rating leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Games and long tasks

All 261 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (66 entries).
  • Pass Models scored 62 models we track, plus 4 other entries on its leaderboard.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Pass Frontier models 9 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on dubesor.de: 225 rows for models we track and 4 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check