ProofBench v1.1
The official leaderboard hasn’t scored a model released after Claude Fable 5.2 (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 18%.
Models write Lean 4 proofs of graduate-level theorems from paired natural-language and formal statements. Scored by the share the Lean checker accepts.
Vals says scores are not comparable with earlier revisions. Four systems tied at 100% on October 29th, 2026 among 54, so it is saturated.
- Made by
- Vals AI
- Released
- August 2026
- Kind
- Formal proofs
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Written proof
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- ProofBench
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last in a system card
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 19th, 2026
4 models share the top score of 100% 4 models share the top score of 100%
Best score per entry from the benchmark's own leaderboard, read on November 19th, 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.
Claude Fable 5.1 leads with 100%, 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. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 100.0 AlephProver
- 100.0 Claude Fable 5.1
- 100.0 Claude Opus 5.5
- 100.0 Claude Sonnet 5.5
- 100.0 Claude Fable 5.2
- 99.0 Claude Opus 5
- 99.0 GPT-6 Astra
- 99.0 GPT-6.1 Sol
- 99.0
Gemini 4 Argon
- 95.0 Claude Fable 5
- 94.0
Muse Wonder Full
- 91.0 Kimi K3.1 Pro
- 89.0 Claude Haiku 5.5
- 87.0 Kimi K3
- 86.0 Aristotle
- 84.0
Muse Wonder
- 83.0 GPT-5.6 Sol
- 83.0 GPT-6 Sol
- 77.0 Claude Sonnet 5
- 75.0
Tencent Hy4 preview
- 74.0 GPT-5.6 Terra
- 70.0 MiMo-V2.6 Pro
- 64.0 GPT-6 Luna
- 63.0 MiMo-V2.6 Flash
- 61.0
Ember-1
- 60.0 GPT-5.6 Luna
- 58.0
Qwen 3.8 Max
- 58.0
Gemini 3.7 Flash
- 58.0
Muse Spark 1.3
- 56.0
DeepSeek V4 Flash 0731
- 54.0
DeepSeek V4.1 Flash
- 51.0 Grok 4.6
- 50.0
DeepSeek V4 Pro 0813
- 49.0 GLM-5.3
- 48.0
Gemini 3.8 Flash
- 43.0
Muse Spark 1.2
- 42.0
Step 5 Preview
- 31.0
Gemini 3.5 Flash
- 31.0 Grok 4.5
- 26.0
Gemini 3.1 Pro
- 26.0 Grok 4.7
- 22.0 MiMo-V2.5-Pro
- 21.0 GLM-5.3-Flash
- 18.0
MiniMax-M3
- 18.0 Beam 1.0
- 16.0 MiMo-V2.5
- 16.0
DeepSeek-V4-Pro
- 16.0
Qwen 3.8 27B
- 10.0
Mistral Large 4 Preview
- 9.00
Mistral Medium 3.5
- 6.00
Inkling-Small
- 3.00 Mercury 2.5
- 0.0
Inkling
- 0.0
Nemotron 3.5 Lightning 30B-A3B
- 1 AlephProver 100%
- 2 Claude Fable 5.1 100%
- 3 Claude Opus 5.5 100%
- 4 Claude Sonnet 5.5 100%
- 5 Claude Fable 5.2 100%
- 6 Claude Opus 5 99%
- 7 GPT-6 Astra 99%
- 8 GPT-6.1 Sol 99%
- 9
Gemini 4 Argon 99%
- 10 Claude Fable 5 95%
- 11
Muse Wonder Full 94%
- 12 Kimi K3.1 Pro 91%
- 13 Claude Haiku 5.5 89%
- 14 Kimi K3 87%
- 15 Aristotle 86%
- 16
Muse Wonder 84%
- 17 GPT-5.6 Sol 83%
- 18 GPT-6 Sol 83%
- 19 Claude Sonnet 5 77%
- 20
Tencent Hy4 preview 75%
- 21 GPT-5.6 Terra 74%
- 22 MiMo-V2.6 Pro 70%
- 23 GPT-6 Luna 64%
- 24 MiMo-V2.6 Flash 63%
- 25
Ember-1 61%
- 26 GPT-5.6 Luna 60%
- 27
Qwen 3.8 Max 58%
- 28
Gemini 3.7 Flash 58%
- 29
Muse Spark 1.3 max 58%
- 30
DeepSeek V4 Flash 0731 56%
- 31
DeepSeek V4.1 Flash 54%
- 32 Grok 4.6 51%
- 33
DeepSeek V4 Pro 0813 50%
- 34 GLM-5.3 49%
- 35
Gemini 3.8 Flash 48%
- 36
Muse Spark 1.2 43%
- 37
Step 5 Preview 42%
- 38
Gemini 3.5 Flash 31%
- 39 Grok 4.5 31%
- 40
Gemini 3.1 Pro 26%
- 41 Grok 4.7 26%
- 42 MiMo-V2.5-Pro 22%
- 43 GLM-5.3-Flash 21%
- 44
MiniMax-M3 18%
- 45 Beam 1.0 18%
- 46 MiMo-V2.5 16%
- 47
DeepSeek-V4-Pro 16%
- 48
Qwen 3.8 27B 16%
- 49
Mistral Large 4 Preview 10%
- 50
Mistral Medium 3.5 9.00%
- 51
Inkling-Small 6.00%
- 52 Mercury 2.5 3.00%
- 53
Inkling 0%
- 54
Nemotron 3.5 Lightning 30B-A3B 0%
Source: Official ProofBench v1.1 leaderboard
- 100.0 Claude Fable 5.1
- 100.0 Claude Opus 5.5
- 100.0 Claude Sonnet 5.5
- 100.0 Claude Fable 5.2
- 99.0 Claude Opus 5
- 99.0 GPT-6 Astra
- 99.0 GPT-6.1 Sol
- 99.0
Gemini 4 Argon
- 95.0 Claude Fable 5
- 94.0
Muse Wonder Full
- 91.0 Kimi K3.1 Pro
- 89.0 Claude Haiku 5.5
- 87.0 Kimi K3
- 84.0
Muse Wonder
- 83.0 GPT-5.6 Sol
- 83.0 GPT-6 Sol
- 77.0 Claude Sonnet 5
- 75.0
Tencent Hy4 preview
- 74.0 GPT-5.6 Terra
- 70.0 MiMo-V2.6 Pro
- 64.0 GPT-6 Luna
- 63.0 MiMo-V2.6 Flash
- 61.0
Ember-1
- 60.0 GPT-5.6 Luna
- 58.0
Qwen 3.8 Max
- 58.0
Gemini 3.7 Flash
- 58.0
Muse Spark 1.3
- 56.0
DeepSeek V4 Flash 0731
- 54.0
DeepSeek V4.1 Flash
- 51.0 Grok 4.6
- 50.0
DeepSeek V4 Pro 0813
- 49.0 GLM-5.3
- 48.0
Gemini 3.8 Flash
- 43.0
Muse Spark 1.2
- 42.0
Step 5 Preview
- 31.0
Gemini 3.5 Flash
- 31.0 Grok 4.5
- 26.0
Gemini 3.1 Pro
- 26.0 Grok 4.7
- 22.0 MiMo-V2.5-Pro
- 21.0 GLM-5.3-Flash
- 18.0
MiniMax-M3
- 18.0 Beam 1.0
- 16.0 MiMo-V2.5
- 16.0
DeepSeek-V4-Pro
- 16.0
Qwen 3.8 27B
- 10.0
Mistral Large 4 Preview
- 9.00
Mistral Medium 3.5
- 6.00
Inkling-Small
- 3.00 Mercury 2.5
- 0.0
Inkling
- 0.0
Nemotron 3.5 Lightning 30B-A3B
- 1 Claude Fable 5.1 100%
- 2 Claude Opus 5.5 100%
- 3 Claude Sonnet 5.5 100%
- 4 Claude Fable 5.2 100%
- 5 Claude Opus 5 99%
- 6 GPT-6 Astra 99%
- 7 GPT-6.1 Sol 99%
- 8
Gemini 4 Argon 99%
- 9 Claude Fable 5 95%
- 10
Muse Wonder Full 94%
- 11 Kimi K3.1 Pro 91%
- 12 Claude Haiku 5.5 89%
- 13 Kimi K3 87%
- 14
Muse Wonder 84%
- 15 GPT-5.6 Sol 83%
- 16 GPT-6 Sol 83%
- 17 Claude Sonnet 5 77%
- 18
Tencent Hy4 preview 75%
- 19 GPT-5.6 Terra 74%
- 20 MiMo-V2.6 Pro 70%
- 21 GPT-6 Luna 64%
- 22 MiMo-V2.6 Flash 63%
- 23
Ember-1 61%
- 24 GPT-5.6 Luna 60%
- 25
Qwen 3.8 Max 58%
- 26
Gemini 3.7 Flash 58%
- 27
Muse Spark 1.3 max 58%
- 28
DeepSeek V4 Flash 0731 56%
- 29
DeepSeek V4.1 Flash 54%
- 30 Grok 4.6 51%
- 31
DeepSeek V4 Pro 0813 50%
- 32 GLM-5.3 49%
- 33
Gemini 3.8 Flash 48%
- 34
Muse Spark 1.2 43%
- 35
Step 5 Preview 42%
- 36
Gemini 3.5 Flash 31%
- 37 Grok 4.5 31%
- 38
Gemini 3.1 Pro 26%
- 39 Grok 4.7 26%
- 40 MiMo-V2.5-Pro 22%
- 41 GLM-5.3-Flash 21%
- 42
MiniMax-M3 18%
- 43 Beam 1.0 18%
- 44 MiMo-V2.5 16%
- 45
DeepSeek-V4-Pro 16%
- 46
Qwen 3.8 27B 16%
- 47
Mistral Large 4 Preview 10%
- 48
Mistral Medium 3.5 9.00%
- 49
Inkling-Small 6.00%
- 50 Mercury 2.5 3.00%
- 51
Inkling 0%
- 52
Nemotron 3.5 Lightning 30B-A3B 0%
Source: Official ProofBench v1.1 leaderboard
- 100.0 Claude Fable 5.1
- 100.0 Claude Opus 5.5
- 100.0 Claude Sonnet 5.5
- 100.0 Claude Fable 5.2
- 99.0 Claude Opus 5
- 99.0 GPT-6 Astra
- 99.0 GPT-6.1 Sol
- 99.0
Gemini 4 Argon
- 95.0 Claude Fable 5
- 94.0
Muse Wonder Full
- 91.0 Kimi K3.1 Pro
- 89.0 Claude Haiku 5.5
- 87.0 Kimi K3
- 84.0
Muse Wonder
- 83.0 GPT-5.6 Sol
- 83.0 GPT-6 Sol
- 77.0 Claude Sonnet 5
- 75.0
Tencent Hy4 preview
- 74.0 GPT-5.6 Terra
- 70.0 MiMo-V2.6 Pro
- 64.0 GPT-6 Luna
- 63.0 MiMo-V2.6 Flash
- 61.0
Ember-1
- 60.0 GPT-5.6 Luna
- 58.0
Qwen 3.8 Max
- 58.0
Gemini 3.7 Flash
- 58.0
Muse Spark 1.3
- 56.0
DeepSeek V4 Flash 0731
- 54.0
DeepSeek V4.1 Flash
- 51.0 Grok 4.6
- 50.0
DeepSeek V4 Pro 0813
- 49.0 GLM-5.3
- 48.0
Gemini 3.8 Flash
- 43.0
Muse Spark 1.2
- 42.0
Step 5 Preview
- 31.0
Gemini 3.5 Flash
- 31.0 Grok 4.5
- 26.0
Gemini 3.1 Pro
- 26.0 Grok 4.7
- 22.0 MiMo-V2.5-Pro
- 21.0 GLM-5.3-Flash
- 18.0
MiniMax-M3
- 18.0 Beam 1.0
- 18.0
Inkling 2 Mini
- 16.0 MiMo-V2.5
- 16.0
DeepSeek-V4-Pro
- 16.0
Qwen 3.8 27B
- 10.0
Mistral Large 4 Preview
- 9.00
Mistral Medium 3.5
- 6.00
Inkling-Small
- 3.00 Mercury 2.5
- 0.0
Inkling
- 0.0
Nemotron 3.5 Lightning 30B-A3B
- 1 Claude Fable 5.1 100%
- 2 Claude Opus 5.5 100%
- 3 Claude Sonnet 5.5 100%
- 4 Claude Fable 5.2 100%
- 5 Claude Opus 5 99%
- 6 GPT-6 Astra 99%
- 7 GPT-6.1 Sol 99%
- 8
Gemini 4 Argon 99%
- 9 Claude Fable 5 95%
- 10
Muse Wonder Full 94%
- 11 Kimi K3.1 Pro 91%
- 12 Claude Haiku 5.5 89%
- 13 Kimi K3 87%
- 14
Muse Wonder 84%
- 15 GPT-5.6 Sol 83%
- 16 GPT-6 Sol 83%
- 17 Claude Sonnet 5 77%
- 18
Tencent Hy4 preview 75%
- 19 GPT-5.6 Terra 74%
- 20 MiMo-V2.6 Pro 70%
- 21 GPT-6 Luna 64%
- 22 MiMo-V2.6 Flash 63%
- 23
Ember-1 61%
- 24 GPT-5.6 Luna 60%
- 25
Qwen 3.8 Max 58%
- 26
Gemini 3.7 Flash 58%
- 27
Muse Spark 1.3 max 58%
- 28
DeepSeek V4 Flash 0731 56%
- 29
DeepSeek V4.1 Flash 54%
- 30 Grok 4.6 51%
- 31
DeepSeek V4 Pro 0813 50%
- 32 GLM-5.3 49%
- 33
Gemini 3.8 Flash 48%
- 34
Muse Spark 1.2 43%
- 35
Step 5 Preview 42%
- 36
Gemini 3.5 Flash 31%
- 37 Grok 4.5 31%
- 38
Gemini 3.1 Pro 26%
- 39 Grok 4.7 26%
- 40 MiMo-V2.5-Pro 22%
- 41 GLM-5.3-Flash 21%
- 42
MiniMax-M3 18%
- 43 Beam 1.0 18%
- 44
Inkling 2 Mini 18%
- 45 MiMo-V2.5 16%
- 46
DeepSeek-V4-Pro 16%
- 47
Qwen 3.8 27B 16%
- 48
Mistral Large 4 Preview 10%
- 49
Mistral Medium 3.5 9.00%
- 50
Inkling-Small 6.00%
- 51 Mercury 2.5 3.00%
- 52
Inkling 0%
- 53
Nemotron 3.5 Lightning 30B-A3B 0%
Sources: Official ProofBench v1.1 leaderboard and labs’ model cards
| # | Entry | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | AlephProver | 100% | Official leaderboard | ||
| 2 | Claude Fable 5.1 | 100% | Sep 2026 | Official leaderboard | |
| 3 | Claude Opus 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 4 | Claude Sonnet 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 5 | Claude Fable 5.2 | 100% | Nov 2026 | Official leaderboard | |
| 6 | Claude Opus 5 | 99% ±2 | Jul 2026 | Official leaderboard | |
| 7 | GPT-6 Astra | 99% ±2 | Sep 2026 | Official leaderboard | |
| 8 | GPT-6.1 Sol | 99% ±2 | Sep 2026 | Official leaderboard | |
| 9 | | 99% ±2 | Sep 2026 | Official leaderboard | |
| 10 | Claude Fable 5 | 95% ±4.3 | Jun 2026 | Official leaderboard | |
| 11 | | 94% ±4.7 | Oct 2026 | Official leaderboard | |
| 12 | Kimi K3.1 Pro | 91% ±5.6 | Oct 2026 | Official leaderboard | |
| 13 | Claude Haiku 5.5 | 89% ±6.2 | Oct 2026 | Official leaderboard | |
| 14 | Kimi K3 | 87% ±6.6 | Jul 2026 | Official leaderboard | |
| 15 | Aristotle | 86% ±6.8 | Official leaderboard | ||
| 16 | | 84% ±7.2 | Oct 2026 | Official leaderboard | |
| 17 | GPT-5.6 Sol | 83% ±7.4 | Jul 2026 | Official leaderboard | |
| 18 | GPT-6 Sol | 83% ±7.4 | Sep 2026 | Official leaderboard | |
| 19 | Claude Sonnet 5 | 77% ±8.3 | Jun 2026 | Official leaderboard | |
| 20 | | 75% ±8.5 | Aug 2026 | Official leaderboard | |
| 21 | GPT-5.6 Terra | 74% ±8.6 | Jul 2026 | Official leaderboard | |
| 22 | MiMo-V2.6 Pro | 70% ±9 | Sep 2026 | Official leaderboard | |
| 23 | GPT-6 Luna | 64% ±9.5 | Sep 2026 | Official leaderboard | |
| 24 | MiMo-V2.6 Flash | 63% ±9.5 | Sep 2026 | Official leaderboard | |
| 25 | | 61% ±9.6 | Sep 2026 | Official leaderboard | |
| 26 | GPT-5.6 Luna | 60% ±9.7 | Jul 2026 | Official leaderboard | |
| 27 | | 58% ±9.7 | Aug 2026 | Official leaderboard | |
| 28 | | 58% ±9.7 | Aug 2026 | Official leaderboard | |
| 29 | | 58% ±9.7 | max | Sep 2026 | Official leaderboard |
| 30 | | 56% ±9.8 | Jul 2026 | Official leaderboard | |
| 31 | | 54% ±9.8 | Sep 2026 | Official leaderboard | |
| 32 | Grok 4.6 | 51% ±9.8 | Aug 2026 | Official leaderboard | |
| 33 | | 50% ±9.8 | Aug 2026 | Official leaderboard | |
| 34 | GLM-5.3 | 49% ±9.8 | Aug 2026 | Official leaderboard | |
| 35 | | 48% ±9.8 | Sep 2026 | Official leaderboard | |
| 36 | | 43% ±9.8 | Aug 2026 | Official leaderboard | |
| 37 | | 42% ±9.7 | Sep 2026 | Official leaderboard | |
| 38 | | 31% ±9.1 | May 2026 | Official leaderboard | |
| 39 | Grok 4.5 | 31% ±9.1 | Jul 2026 | Official leaderboard | |
| 40 | | 26% ±8.6 | Feb 2026 | Official leaderboard | |
| 41 | Grok 4.7 | 26% ±8.6 | Sep 2026 | Official leaderboard | |
| 42 | MiMo-V2.5-Pro | 22% ±8.2 | Apr 2026 | Official leaderboard | |
| 43 | GLM-5.3-Flash | 21% ±8 | Aug 2026 | Official leaderboard | |
| 44 | | 18% ±7.6 | Jun 2026 | Official leaderboard | |
| 45 | Beam 1.0 | 18% ±7.6 | Oct 2026 | Official leaderboard | |
| 46 | MiMo-V2.5 | 16% ±7.2 | Apr 2026 | Official leaderboard | |
| 47 | | 16% ±7.2 | Apr 2026 | Official leaderboard | |
| 48 | | 16% ±7.2 | Aug 2026 | Official leaderboard | |
| 49 | | 10% ±5.9 | Oct 2026 | Official leaderboard | |
| 50 | | 9.00% ±5.6 | Apr 2026 | Official leaderboard | |
| 51 | | 6.00% ±4.7 | Jul 2026 | Official leaderboard | |
| 52 | Mercury 2.5 | 3.00% ±3.4 | Sep 2026 | Official leaderboard | |
| 53 | | 0% | Jul 2026 | Official leaderboard | |
| 54 | | 0% | Aug 2026 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 100% | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 3 | Claude Sonnet 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 4 | Claude Fable 5.2 | 100% | Nov 2026 | Official leaderboard | |
| 5 | Claude Opus 5 | 99% ±2 | Jul 2026 | Official leaderboard | |
| 6 | GPT-6 Astra | 99% ±2 | Sep 2026 | Official leaderboard | |
| 7 | GPT-6.1 Sol | 99% ±2 | Sep 2026 | Official leaderboard | |
| 8 | | 99% ±2 | Sep 2026 | Official leaderboard | |
| 9 | Claude Fable 5 | 95% ±4.3 | Jun 2026 | Official leaderboard | |
| 10 | | 94% ±4.7 | Oct 2026 | Official leaderboard | |
| 11 | Kimi K3.1 Pro | 91% ±5.6 | Oct 2026 | Official leaderboard | |
| 12 | Claude Haiku 5.5 | 89% ±6.2 | Oct 2026 | Official leaderboard | |
| 13 | Kimi K3 | 87% ±6.6 | Jul 2026 | Official leaderboard | |
| 14 | | 84% ±7.2 | Oct 2026 | Official leaderboard | |
| 15 | GPT-5.6 Sol | 83% ±7.4 | Jul 2026 | Official leaderboard | |
| 16 | GPT-6 Sol | 83% ±7.4 | Sep 2026 | Official leaderboard | |
| 17 | Claude Sonnet 5 | 77% ±8.3 | Jun 2026 | Official leaderboard | |
| 18 | | 75% ±8.5 | Aug 2026 | Official leaderboard | |
| 19 | GPT-5.6 Terra | 74% ±8.6 | Jul 2026 | Official leaderboard | |
| 20 | MiMo-V2.6 Pro | 70% ±9 | Sep 2026 | Official leaderboard | |
| 21 | GPT-6 Luna | 64% ±9.5 | Sep 2026 | Official leaderboard | |
| 22 | MiMo-V2.6 Flash | 63% ±9.5 | Sep 2026 | Official leaderboard | |
| 23 | | 61% ±9.6 | Sep 2026 | Official leaderboard | |
| 24 | GPT-5.6 Luna | 60% ±9.7 | Jul 2026 | Official leaderboard | |
| 25 | | 58% ±9.7 | Aug 2026 | Official leaderboard | |
| 26 | | 58% ±9.7 | Aug 2026 | Official leaderboard | |
| 27 | | 58% ±9.7 | max | Sep 2026 | Official leaderboard |
| 28 | | 56% ±9.8 | Jul 2026 | Official leaderboard | |
| 29 | | 54% ±9.8 | Sep 2026 | Official leaderboard | |
| 30 | Grok 4.6 | 51% ±9.8 | Aug 2026 | Official leaderboard | |
| 31 | | 50% ±9.8 | Aug 2026 | Official leaderboard | |
| 32 | GLM-5.3 | 49% ±9.8 | Aug 2026 | Official leaderboard | |
| 33 | | 48% ±9.8 | Sep 2026 | Official leaderboard | |
| 34 | | 43% ±9.8 | Aug 2026 | Official leaderboard | |
| 35 | | 42% ±9.7 | Sep 2026 | Official leaderboard | |
| 36 | | 31% ±9.1 | May 2026 | Official leaderboard | |
| 37 | Grok 4.5 | 31% ±9.1 | Jul 2026 | Official leaderboard | |
| 38 | | 26% ±8.6 | Feb 2026 | Official leaderboard | |
| 39 | Grok 4.7 | 26% ±8.6 | Sep 2026 | Official leaderboard | |
| 40 | MiMo-V2.5-Pro | 22% ±8.2 | Apr 2026 | Official leaderboard | |
| 41 | GLM-5.3-Flash | 21% ±8 | Aug 2026 | Official leaderboard | |
| 42 | | 18% ±7.6 | Jun 2026 | Official leaderboard | |
| 43 | Beam 1.0 | 18% ±7.6 | Oct 2026 | Official leaderboard | |
| 44 | MiMo-V2.5 | 16% ±7.2 | Apr 2026 | Official leaderboard | |
| 45 | | 16% ±7.2 | Apr 2026 | Official leaderboard | |
| 46 | | 16% ±7.2 | Aug 2026 | Official leaderboard | |
| 47 | | 10% ±5.9 | Oct 2026 | Official leaderboard | |
| 48 | | 9.00% ±5.6 | Apr 2026 | Official leaderboard | |
| 49 | | 6.00% ±4.7 | Jul 2026 | Official leaderboard | |
| 50 | Mercury 2.5 | 3.00% ±3.4 | Sep 2026 | Official leaderboard | |
| 51 | | 0% | Jul 2026 | Official leaderboard | |
| 52 | | 0% | Aug 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 100% | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 3 | Claude Sonnet 5.5 | 100% | Sep 2026 | Official leaderboard | |
| 4 | Claude Fable 5.2 | 100% | Nov 2026 | Official leaderboard | |
| 5 | Claude Opus 5 | 99% | Jul 2026 | Official leaderboard | |
| 6 | GPT-6 Astra | 99% | Sep 2026 | Official leaderboard | |
| 7 | GPT-6.1 Sol | 99% | Sep 2026 | Official leaderboard | |
| 8 | 99% | Sep 2026 | Official leaderboard | ||
| 9 | Claude Fable 5 | 95% | Jun 2026 | Official leaderboard | |
| 10 | 94% | Oct 2026 | Official leaderboard | ||
| 11 | Kimi K3.1 Pro | 91% | Oct 2026 | Official leaderboard | |
| 12 | Claude Haiku 5.5 | 89% | Oct 2026 | Official leaderboard | |
| 13 | Kimi K3 | 87% | Jul 2026 | Official leaderboard | |
| 14 | 84% | Oct 2026 | Official leaderboard | ||
| 15 | GPT-5.6 Sol | 83% | Jul 2026 | Official leaderboard | |
| 16 | GPT-6 Sol | 83% | Sep 2026 | Official leaderboard | |
| 17 | Claude Sonnet 5 | 77% | Jun 2026 | Official leaderboard | |
| 18 | 75% | Aug 2026 | Official leaderboard | ||
| 19 | GPT-5.6 Terra | 74% | Jul 2026 | Official leaderboard | |
| 20 | MiMo-V2.6 Pro | 70% | Sep 2026 | Official leaderboard | |
| 21 | GPT-6 Luna | 64% | Sep 2026 | Official leaderboard | |
| 22 | MiMo-V2.6 Flash | 63% | Sep 2026 | Official leaderboard | |
| 23 | 61% | Sep 2026 | Official leaderboard | ||
| 24 | GPT-5.6 Luna | 60% | Jul 2026 | Official leaderboard | |
| 25 | 58% | Aug 2026 | Official leaderboard | ||
| 26 | 58% | Aug 2026 | Official leaderboard | ||
| 27 | 58% | max | Sep 2026 | Official leaderboard | |
| 28 | 56% | Jul 2026 | Official leaderboard | ||
| 29 | 54% | Sep 2026 | Official leaderboard | ||
| 30 | Grok 4.6 | 51% | Aug 2026 | Official leaderboard | |
| 31 | 50% | Aug 2026 | Official leaderboard | ||
| 32 | GLM-5.3 | 49% | Aug 2026 | Official leaderboard | |
| 33 | 48% | Sep 2026 | Official leaderboard | ||
| 34 | 43% | Aug 2026 | Official leaderboard | ||
| 35 | 42% | Sep 2026 | Official leaderboard | ||
| 36 | 31% | May 2026 | Official leaderboard | ||
| 37 | Grok 4.5 | 31% | Jul 2026 | Official leaderboard | |
| 38 | 26% | Feb 2026 | Official leaderboard | ||
| 39 | Grok 4.7 | 26% | Sep 2026 | Official leaderboard | |
| 40 | MiMo-V2.5-Pro | 22% | Apr 2026 | Official leaderboard | |
| 41 | GLM-5.3-Flash | 21% | Aug 2026 | Official leaderboard | |
| 42 | 18% | Jun 2026 | Official leaderboard | ||
| 43 | Beam 1.0 | 18% | Oct 2026 | Official leaderboard | |
| 44 | 18% | Nov 2026 | Lab model card | ||
| 45 | MiMo-V2.5 | 16% | Apr 2026 | Official leaderboard | |
| 46 | 16% | Apr 2026 | Official leaderboard | ||
| 47 | 16% | Aug 2026 | Official leaderboard | ||
| 48 | 10% | Oct 2026 | Official leaderboard | ||
| 49 | 9.00% | Apr 2026 | Official leaderboard | ||
| 50 | 6.00% | Jul 2026 | Official leaderboard | ||
| 51 | Mercury 2.5 | 3.00% | Sep 2026 | Official leaderboard | |
| 52 | 0% | Jul 2026 | Official leaderboard | ||
| 53 | 0% | Aug 2026 | Official leaderboard |
Labs report scores for 1 model in their cards. Switch the scores above to rank them together.
Accuracy against latency
The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Latency (mean per test) |
|---|---|---|---|
| Claude Fable 5.2 | 100% | 170.86 s | |
| Claude Sonnet 5.5 | 100% | 347.58 s | |
| Claude Opus 5.5 | 100% | 351.04 s | |
| Claude Fable 5.1 | 100% | 478.3 s | |
| AlephProver | 100% | 1,108 s | |
| GPT-6.1 Sol | 99% | 284.7 s | |
| GPT-6 Astra | 99% | 307.87 s | |
| 99% | 380.25 s | ||
| Claude Opus 5 | 99% | 590.89 s | |
| Claude Fable 5 | 95% | 822.74 s | |
| 94% | 695.56 s | ||
| Kimi K3.1 Pro | 91% | 496.16 s | |
| Claude Haiku 5.5 | 89% | 418.05 s | |
| Kimi K3 | 87% | 2,071 s | |
| 84% | 929.05 s | ||
| GPT-6 Sol | 83% | 304.51 s | |
| GPT-5.6 Sol | 83% | 520.4 s | |
| Claude Sonnet 5 | 77% | 898.08 s | |
| 75% | 1,374 s | ||
| GPT-5.6 Terra | 74% | 777.34 s | |
| MiMo-V2.6 Pro | 70% | 3,694 s | |
| GPT-6 Luna | 64% | 451.48 s | |
| MiMo-V2.6 Flash | 63% | 3,770 s | |
| 61% | 1,269 s | ||
| GPT-5.6 Luna | 60% | 513.69 s | |
| 58% | 423.7 s | ||
| max | 58% | 568.7 s | |
| 58% | 1,868 s | ||
| 56% | 933.98 s | ||
| 55% | 534.06 s | ||
| 54% | 546.6 s | ||
| Grok 4.6 | 51% | 861.9 s | |
| 50% | 732.37 s | ||
| GLM-5.3 | 49% | 2,543 s | |
| 48% | 368.65 s | ||
| 43% | 469.15 s | ||
| 42% | 2,314 s | ||
| 31% | 394.48 s | ||
| Grok 4.5 | 31% | 668.86 s | |
| Grok 4.7 | 26% | 767.18 s | |
| 26% | 889.06 s | ||
| MiMo-V2.5-Pro | 22% | 1,177 s | |
| GLM-5.3-Flash | 21% | 4,275 s | |
| Beam 1.0 | 18% | 266.66 s | |
| 18% | 718.66 s | ||
| 16% | 423.45 s | ||
| MiMo-V2.5 | 16% | 1,256 s | |
| 16% | 1,454 s | ||
| 10% | 1,259 s | ||
| 9% | 479.05 s | ||
| 6% | 507.3 s | ||
| Mercury 2.5 | 3% | 201.72 s | |
| 0% | 436.43 s | ||
| 0% | 919.25 s |
Accuracy against latency
The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Latency (mean per test) |
|---|---|---|---|
| Claude Fable 5.2 | 100% | 170.86 s | |
| Claude Sonnet 5.5 | 100% | 347.58 s | |
| Claude Opus 5.5 | 100% | 351.04 s | |
| Claude Fable 5.1 | 100% | 478.3 s | |
| GPT-6.1 Sol | 99% | 284.7 s | |
| GPT-6 Astra | 99% | 307.87 s | |
| 99% | 380.25 s | ||
| Claude Opus 5 | 99% | 590.89 s | |
| Claude Fable 5 | 95% | 822.74 s | |
| 94% | 695.56 s | ||
| Kimi K3.1 Pro | 91% | 496.16 s | |
| Claude Haiku 5.5 | 89% | 418.05 s | |
| Kimi K3 | 87% | 2,071 s | |
| 84% | 929.05 s | ||
| GPT-6 Sol | 83% | 304.51 s | |
| GPT-5.6 Sol | 83% | 520.4 s | |
| Claude Sonnet 5 | 77% | 898.08 s | |
| 75% | 1,374 s | ||
| GPT-5.6 Terra | 74% | 777.34 s | |
| MiMo-V2.6 Pro | 70% | 3,694 s | |
| GPT-6 Luna | 64% | 451.48 s | |
| MiMo-V2.6 Flash | 63% | 3,770 s | |
| 61% | 1,269 s | ||
| GPT-5.6 Luna | 60% | 513.69 s | |
| 58% | 423.7 s | ||
| max | 58% | 568.7 s | |
| 58% | 1,868 s | ||
| 56% | 933.98 s | ||
| 55% | 534.06 s | ||
| 54% | 546.6 s | ||
| Grok 4.6 | 51% | 861.9 s | |
| 50% | 732.37 s | ||
| GLM-5.3 | 49% | 2,543 s | |
| 48% | 368.65 s | ||
| 43% | 469.15 s | ||
| 42% | 2,314 s | ||
| 31% | 394.48 s | ||
| Grok 4.5 | 31% | 668.86 s | |
| Grok 4.7 | 26% | 767.18 s | |
| 26% | 889.06 s | ||
| MiMo-V2.5-Pro | 22% | 1,177 s | |
| GLM-5.3-Flash | 21% | 4,275 s | |
| Beam 1.0 | 18% | 266.66 s | |
| 18% | 718.66 s | ||
| 16% | 423.45 s | ||
| MiMo-V2.5 | 16% | 1,256 s | |
| 16% | 1,454 s | ||
| 10% | 1,259 s | ||
| 9% | 479.05 s | ||
| 6% | 507.3 s | ||
| Mercury 2.5 | 3% | 201.72 s | |
| 0% | 436.43 s | ||
| 0% | 919.25 s |
The best score, 100%, costs $0.52 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol comes within 1 points of the best for $0.23 a task, about half the cost. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official ProofBench v1.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | 100% | $2.70 | 41,014 | ||
| Claude Opus 5.5 | 100% | $0.92 | 34,454 | ||
| Claude Sonnet 5.5 | 100% | $0.52 | 38,174 | ||
| Claude Fable 5.2 | 100% | $0.79 | 15,270 | ||
| Claude Opus 5 | 99% | $1.79 | 47,697 | ||
| GPT-6 Astra | 99% | $1.71 | 9,972 | ||
| GPT-6.1 Sol | 99% | $0.23 | 10,381 | ||
| 99% | $0.78 | 16,943 | |||
| Claude Fable 5 | 95% | $5.23 | 71,846 | ||
| 94% | $0.86 | 27,090 | |||
| Kimi K3.1 Pro | 91% | $0.47 | 22,381 | ||
| Claude Haiku 5.5 | 89% | $0.17 | 96,721 | ||
| Kimi K3 | 87% | $1.65 | 73,191 | ||
| 84% | $1.31 | 36,876 | |||
| GPT-5.6 Sol | 83% | $1.44 | 15,376 | ||
| GPT-6 Sol | 83% | $0.48 | 13,630 | ||
| Claude Sonnet 5 | 77% | $1.37 | 75,841 | ||
| 75% | $0.34 | 70,300 | |||
| GPT-5.6 Terra | 74% | $1.27 | 15,580 | ||
| MiMo-V2.6 Pro | 70% | $0.25 | 156,532 | ||
| GPT-6 Luna | 64% | $0.04 | 26,528 | ||
| MiMo-V2.6 Flash | 63% | $0.12 | 242,145 | ||
| 61% | $1.74 | 72,478 | |||
| GPT-5.6 Luna | 60% | $0.12 | 19,442 | ||
| 58% | $1.50 | 109,428 | |||
| 58% | $0.56 | 13,973 | |||
| max | 58% | $0.48 | 45,292 | ||
| 56% | $0.16 | 74,456 | |||
| 55% | $0.43 | 36,064 | |||
| 54% | $0.13 | 81,902 | |||
| Grok 4.6 | 51% | $0.82 | 38,271 | ||
| 50% | $0.26 | 24,345 | |||
| GLM-5.3 | 49% | $2.08 | 195,563 | ||
| 48% | $0.60 | 12,467 | |||
| 43% | $0.44 | 38,717 | |||
| 42% | $0.71 | 133,184 | |||
| 31% | $0.57 | 14,092 | |||
| Grok 4.5 | 31% | $0.57 | 23,013 | ||
| 26% | $0.78 | 21,000 | |||
| Grok 4.7 | 26% | $0.79 | 14,226 | ||
| MiMo-V2.5-Pro | 22% | $0.09 | 53,015 | ||
| GLM-5.3-Flash | 21% | $0.45 | 333,212 | ||
| 18% | $0.42 | 48,763 | |||
| Beam 1.0 | 18% | 17,850 | |||
| MiMo-V2.5 | 16% | $0.06 | 119,561 | ||
| 16% | $0.14 | 16,116 | |||
| 16% | $2.30 | 169,025 | |||
| 10% | $0.33 | 18,237 | |||
| 9.00% | $1.30 | 21,134 | |||
| 6.00% | $0.08 | 25,970 | |||
| Mercury 2.5 | 3.00% | $0.04 | 15,608 | ||
| 0% | $0.20 | 14,174 | |||
| 0% | $0.02 | 51,314 |
The best score, 100%, costs $0.52 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol comes within 1 points of the best for $0.23 a task, about half the cost. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official ProofBench v1.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | 100% | $2.70 | 41,014 | ||
| Claude Opus 5.5 | 100% | $0.92 | 34,454 | ||
| Claude Sonnet 5.5 | 100% | $0.52 | 38,174 | ||
| Claude Fable 5.2 | 100% | $0.79 | 15,270 | ||
| Claude Opus 5 | 99% | $1.79 | 47,697 | ||
| GPT-6 Astra | 99% | $1.71 | 9,972 | ||
| GPT-6.1 Sol | 99% | $0.23 | 10,381 | ||
| 99% | $0.78 | 16,943 | |||
| Claude Fable 5 | 95% | $5.23 | 71,846 | ||
| 94% | $0.86 | 27,090 | |||
| Kimi K3.1 Pro | 91% | $0.47 | 22,381 | ||
| Claude Haiku 5.5 | 89% | $0.17 | 96,721 | ||
| Kimi K3 | 87% | $1.65 | 73,191 | ||
| 84% | $1.31 | 36,876 | |||
| GPT-5.6 Sol | 83% | $1.44 | 15,376 | ||
| GPT-6 Sol | 83% | $0.48 | 13,630 | ||
| Claude Sonnet 5 | 77% | $1.37 | 75,841 | ||
| 75% | $0.34 | 70,300 | |||
| GPT-5.6 Terra | 74% | $1.27 | 15,580 | ||
| MiMo-V2.6 Pro | 70% | $0.25 | 156,532 | ||
| GPT-6 Luna | 64% | $0.04 | 26,528 | ||
| MiMo-V2.6 Flash | 63% | $0.12 | 242,145 | ||
| 61% | $1.74 | 72,478 | |||
| GPT-5.6 Luna | 60% | $0.12 | 19,442 | ||
| 58% | $1.50 | 109,428 | |||
| 58% | $0.56 | 13,973 | |||
| max | 58% | $0.48 | 45,292 | ||
| 56% | $0.16 | 74,456 | |||
| 55% | $0.43 | 36,064 | |||
| 54% | $0.13 | 81,902 | |||
| Grok 4.6 | 51% | $0.82 | 38,271 | ||
| 50% | $0.26 | 24,345 | |||
| GLM-5.3 | 49% | $2.08 | 195,563 | ||
| 48% | $0.60 | 12,467 | |||
| 43% | $0.44 | 38,717 | |||
| 42% | $0.71 | 133,184 | |||
| 31% | $0.57 | 14,092 | |||
| Grok 4.5 | 31% | $0.57 | 23,013 | ||
| 26% | $0.78 | 21,000 | |||
| Grok 4.7 | 26% | $0.79 | 14,226 | ||
| MiMo-V2.5-Pro | 22% | $0.09 | 53,015 | ||
| GLM-5.3-Flash | 21% | $0.45 | 333,212 | ||
| 18% | $0.42 | 48,763 | |||
| Beam 1.0 | 18% | 17,850 | |||
| MiMo-V2.5 | 16% | $0.06 | 119,561 | ||
| 16% | $0.14 | 16,116 | |||
| 16% | $2.30 | 169,025 | |||
| 10% | $0.33 | 18,237 | |||
| 9.00% | $1.30 | 21,134 | |||
| 6.00% | $0.08 | 25,970 | |||
| Mercury 2.5 | 3.00% | $0.04 | 15,608 | ||
| 0% | $0.20 | 14,174 | |||
| 0% | $0.02 | 51,314 |
2 models have held number one on the official leaderboard since its release in August 2026 2 models have held number one with claims included since its release in August 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official ProofBench v1.1 leaderboard
Claude Fable 5 on the official leaderboard passed 85% in June 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official ProofBench v1.1 leaderboard and labs’ model cards
Labs report it only in system cards
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark. Some system cards do, below.
One system card reports it
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.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 20, 2026 | | 18 | ProofBench v1.1 | Capabilities |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More in Math
- AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
- IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
- HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
- PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked.
Qwen3.7-Max 86.5%
- MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
- MathArena Apex Shortlist In use Models solve 47 hard final-answer problems that MathArena selected from 2025 competitions, where the best models scored about 50% at selection. Scored by accuracy over repeated attempts. GPT-5.5 98.4%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (54 entries) and system cards (1 score).
- Pass Models scored 53 models we track, plus 2 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
- Pass Frontier models 7 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Note Headroom Saturated. The best is 100%, past 85% since June 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on vals.ai: 53 rows for models we track and 2 other entries at the last read.
- Pass Last read November 19th, 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.