OTIS Mock AIME leaderboard
- Claude Fable 5 leads
- 100.0%
- models measured
- 117
- at the top
- Tied
- median
- 86.7%
Leader on OTIS Mock AIME · read October 22
On October 22, 2026, 132 of our catalog's models had a OTIS Mock AIME result, and Anthropic Claude Fable 5 led with 100.0%.
Competition math in the style of the AIME, from the OTIS mock exams, each answer a whole number. Share solved, run by Epoch AI.
Role in the index
OTIS Mock AIME carries 40% of the Math Index. A model missing it is scored on the other benchmarks of that index. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Fable 5Anthropic | 100.0% | 79.3 | $50.00 | |
| 2 | Claude Fable 5.1Anthropic | 100.0% | 84.2 | $50.00 | |
| 3 | Claude Opus 5.5Anthropic | 100.0% | 88.8 | $20.00 | |
| 4 | Claude Sonnet 5.5Anthropic | 100.0% | 87.3 | $10.00 | |
| 5 | Gemini 4 ArgonGoogle | 100.0% | 81.0 | $10.00 | |
| 6 | GPT-5.6 SolOpenAI | 100.0% | 73.5 | $20.00 | |
| 7 | GPT-6 AstraOpenAI | 100.0% | 85.1 | $50.00 | |
| 8 | GPT-6 SolOpenAI | 100.0% | 76.0 | $10.00 | |
| 9 | GPT-6.1 SolOpenAI | 100.0% | 82.4 | $10.00 | |
| 10 | Qwen3.8 Max (0902)Qwen | 100.0% | 62.4 | $6.00 | |
| 11 | GPT-5.6 TerraOpenAI | 99.7% | 63.9 | $12.00 | |
| 12 | DeepSeek V4.1 Flash 1017DeepSeek | 99.4% | 70.3 | $0.60 | |
| 13 | Muse Spark 1.3Meta | 99.2% | 57.4 | $4.25 | |
| 14 | Grok 4.6xAI | 99.2% | 65.7 | $6.00 | |
| 15 | Claude Haiku 5.5Anthropic | 98.9% | 70.7 | $0.50 | |
| 16 | Claude Opus 5Anthropic | 98.9% | 83.0 | $25.00 | |
| 17 | Gemini 3.8 FlashGoogle | 98.9% | 61.6 | $3.75 | |
| 18 | GPT-6 LunaOpenAI | 98.9% | 57.3 | $0.50 | |
| 19 | DeepSeek V4 Pro 0813DeepSeek | 98.6% | 56.1 | $1.98 | |
| 20 | Claude Opus 4.8Anthropic | 98.3% | 65.0 | $25.00 | |
| 21 | DeepSeek V4.1 FlashDeepSeek | 98.3% | 62.5 | $0.84 | |
| 22 | Mistral Large 4Mistral AI | 98.3% | 56.4 | $4.18 | |
| 23 | GPT-5.6 LunaOpenAI | 98.3% | 58.0 | $1.20 | |
| 24 | Grok 4.7xAI | 98.1% | 66.7 | $6.00 | |
| 25 | Claude Opus 4.7Anthropic | 97.8% | 67.5 | $25.00 | |
| 26 | GPT-5.4OpenAI | 97.8% | 64.4 | $15.00 | |
| 27 | Grok 4.5xAI | 97.8% | 58.6 | $6.00 | |
| 28 | Gemini 3.7 FlashGoogle | 97.2% | 58.0 | $3.75 | |
| 29 | Kimi K3Moonshot AI | 97.2% | 62.3 | $15.00 | |
| 30 | DeepSeek V4 Pro 0423DeepSeek | 96.7% | 38.7 | $2.976 | |
| 31 | Kimi K2.6Moonshot AI | 96.1% | 52.1 | $4.00 | |
| 32 | GPT-5.2OpenAI | 96.1% | 55.9 | $14.00 | |
| 33 | Gemini 3.1 Pro PreviewGoogle | 95.6% | 32.3 | $12.00 | |
| 34 | Gemini 3 Flash PreviewGoogle | 95.6% | 43.7 | $3.00 | |
| 35 | Gemini 3.5 FlashGoogle | 95.6% | 39.8 | $9.00 | |
| 36 | Kimi K2.7 CodeMoonshot AI | 95.6% | 53.4 | $4.00 | |
| 37 | Qwen3.7 MaxQwen | 95.6% | 54.1 | $4.425 | |
| 38 | Claude Sonnet 5Anthropic | 94.7% | 57.7 | $10.00 | |
| 39 | Claude Opus 4.6Anthropic | 94.4% | 57.2 | $25.00 | |
| 40 | DeepSeek V4 Flash 0731DeepSeek | 94.4% | 51.8 | $0.396 | |
| 41 | Gemini 3.6 FlashGoogle | 94.2% | 62.5 | $3.75 | |
| 42 | GLM 5.3 FlashZ.ai | 93.9% | 57.7 | $0.50 | |
| 43 | Qwen3.6 PlusQwen | 93.3% | 44.1 | $1.95 | |
| 44 | Qwen3.7 PlusQwen | 93.3% | 33.2 | $1.28 | |
| 45 | Grok 4.3xAI | 93.3% | 37.4 | $2.50 | |
| 46 | GLM 5.1Z.ai | 93.3% | 49.2 | $4.40 | |
| 47 | GPT-5OpenAI | 91.4% | 38.8 | $10.00 | |
| 48 | Qwen3.6 27BQwen | 91.1% | 36.8 | $2.70 | |
| 49 | GLM 5.3Z.ai | 91.1% | 70.6 | $4.40 | |
| 50 | T Inkling SmallThinking Machines | 90.0% | 27.3 | $1.20 | |
| 51 | GPT-5.4 MiniOpenAI | 88.9% | 35.8 | $4.50 | |
| 52 | gpt-oss-120bOpenAI | 88.9% | Not benchmarked | $0.50 | |
| 53 | Qwen3.5 397B A17BQwen | 88.9% | Not benchmarked | $2.34 | |
| 54 | T InklingThinking Machines | 88.9% | 31.5 | $4.05 | |
| 55 | GPT-5.1OpenAI | 88.6% | 40.4 | $10.00 | |
| 56 | GPT-5.4 NanoOpenAI | 87.8% | 44.8 | $1.25 | |
| 57 | Nemotron 3 UltraNVIDIA | 86.7% | 30.0 | $2.40 | |
| 58 | GPT-5 MiniOpenAI | 86.7% | 34.2 | $2.00 | |
| 59 | Qwen3 235B A22B Thinking 2507Qwen | 86.7% | Not benchmarked | $3.50 | |
| 60 | Qwen3.5 Plus 2026-04-20Qwen | 86.7% | 39.5 | $1.80 | |
| 61 | Qwen3.6 35B A3BQwen | 86.7% | Not benchmarked | $1.00 | |
| 62 | Qwen3.7 FlashQwen | 86.7% | Not benchmarked | $0.13 | |
| 63 | GLM 5.2Z.ai | 86.4% | 61.1 | $4.40 | |
| 64 | Claude Opus 4.5Anthropic | 86.1% | 44.0 | $25.00 | |
| 65 | Claude Sonnet 4.6Anthropic | 85.8% | 57.3 | $15.00 | |
| 66 | Gemini 2.5 ProGoogle | 84.7% | 19.1 | $10.00 | |
| 67 | GPT-5.5OpenAI | 84.4% | 71.3 | $30.00 | |
| 68 | o3OpenAI | 84.4% | Not benchmarked | $8.00 | |
| 69 | Qwen3.5-FlashQwen | 84.4% | 41.1 | $0.26 | |
| 70 | Qwen3.6 FlashQwen | 84.4% | Not benchmarked | $1.125 | |
| 71 | GLM 4.7Z.ai | 83.3% | 55.1 | $2.20 | |
| 72 | Gemma 4 26B A4BGoogle | 82.2% | Not benchmarked | $0.60 | |
| 73 | o4 MiniOpenAI | 81.7% | Not benchmarked | $4.40 | |
| 74 | GPT-5 NanoOpenAI | 81.1% | Not benchmarked | $0.40 | |
| 75 | Gemini 3.1 Flash LiteGoogle | 80.0% | Not benchmarked | $1.50 | |
| 76 | GLM 5Z.ai | 80.0% | 41.7 | $3.20 | |
| 77 | Claude Sonnet 4.5Anthropic | 77.8% | 39.5 | $15.00 | |
| 78 | o3 MiniOpenAI | 76.9% | Not benchmarked | $4.40 | |
| 79 | Gemma 4 31BGoogle | 73.3% | 39.0 | $0.40 | |
| 80 | o1OpenAI | 73.3% | Not benchmarked | $60.00 | |
| 81 | Gemini 3.5 Flash LiteGoogle | 71.1% | 49.0 | $2.50 | |
| 82 | MiniMax M3MiniMax | 71.1% | 39.2 | $1.20 | |
| 83 | Qwen3.5-35B-A3BQwen | 70.0% | Not benchmarked | $1.30 | |
| 84 | Claude Opus 4.1Anthropic | 68.9% | Not benchmarked | $75.00 | |
| 85 | Qwen3 32BQwen | 66.9% | Not benchmarked | $0.40 | |
| 86 | Claude Haiku 4.5Anthropic | 66.7% | 35.6 | $5.00 | |
| 87 | R1 0528DeepSeek | 66.4% | Not benchmarked | $2.18 | |
| 88 | Qwen3 14BQwen | 66.4% | Not benchmarked | $0.23 | |
| 89 | gpt-oss-20bOpenAI | 65.3% | Not benchmarked | $0.15 | |
| 90 | Claude Opus 4RetiredAnthropic | 64.4% | Not benchmarked | $75.00 | |
| 91 | Qwen3 30B A3BQwen | 62.8% | Not benchmarked | $0.50 | |
| 92 | Qwen3 30B A3B Instruct 2507Qwen | 62.2% | Not benchmarked | $0.30 | |
| 93 | Qwen3.5-9BQwen | 61.7% | Not benchmarked | $0.15 | |
| 94 | GLM 4.7 FlashZ.ai | 58.3% | Not benchmarked | $0.40 | |
| 95 | Claude 3.7 SonnetRetiredAnthropic | 57.8% | Not benchmarked | $15.00 | |
| 96 | Grok 3RetiredxAI | 55.6% | Not benchmarked | $15.00 | |
| 97 | R1RetiredDeepSeek | 53.3% | Not benchmarked | $2.50 | |
| 98 | DeepSeek V3DeepSeek | 48.9% | Not benchmarked | $0.9594 | |
| 99 | o1-miniRetiredOpenAI | 46.9% | Not benchmarked | $4.40 | |
| 100 | GPT-4.1 MiniOpenAI | 44.7% | Not benchmarked | $1.60 | |
| 101 | GPT-4.1OpenAI | 38.3% | Not benchmarked | $8.00 | |
| 102 | DeepSeek V3 0324DeepSeek | 37.8% | Not benchmarked | $1.07 | |
| 103 | Gemini 2.0 FlashRetiredGoogle | 31.1% | Not benchmarked | $0.40 | |
| 104 | GPT-4.1 NanoOpenAI | 28.9% | Not benchmarked | $0.40 | |
| 105 | Gemini 1.5 ProRetiredGoogle | 23.1% | Not benchmarked | $5.00 | |
| 106 | Gemma 3 27BGoogle | 22.5% | Not benchmarked | $0.30 | |
| 107 | Qwen-PlusQwen | 17.8% | Not benchmarked | $0.78 | |
| 108 | Gemma 3 12BGoogle | 16.7% | Not benchmarked | $0.1625 | |
| 109 | Gemini 1.5 FlashRetiredGoogle | 16.3% | Not benchmarked | $0.30 | |
| 110 | Phi 4Microsoft | 13.8% | Not benchmarked | $0.14 | |
| 111 | Grok 2RetiredxAI | 11.5% | Not benchmarked | $10.00 | |
| 112 | Claude 3.5 SonnetRetiredAnthropic | 8.5% | Not benchmarked | $15.00 | |
| 113 | Mistral Large 2407Mistral AI | 8.5% | Not benchmarked | $6.00 | |
| 114 | Qwen2.5 72B InstructQwen | 8.1% | Not benchmarked | $0.40 | |
| 115 | Llama 4 ScoutMeta Llama | 7.8% | Not benchmarked | $0.50 | |
| 116 | Gemma 3 4BGoogle | 7.5% | Not benchmarked | $0.075 | |
| 117 | GPT-4o-mini (2024-07-18)OpenAI | 6.9% | Not benchmarked | $0.60 | |
| 118 | GPT-4o (2024-08-06)OpenAI | 6.4% | Not benchmarked | $10.00 | |
| 119 | GPT-4o (2024-05-13)OpenAI | 6.3% | Not benchmarked | $15.00 | |
| 120 | GPT-4o (2024-11-20)OpenAI | 6.3% | Not benchmarked | $10.00 | |
| 121 | Llama 3.3 70B InstructMeta Llama | 5.1% | Not benchmarked | $0.72 | |
| 122 | Claude 3 OpusRetiredAnthropic | 4.7% | Not benchmarked | $75.00 | |
| 123 | Claude 3.5 HaikuRetiredAnthropic | 4.3% | Not benchmarked | $4.00 | |
| 124 | Llama 3.1 70B InstructMeta Llama | 3.6% | Not benchmarked | $0.56 | |
| 125 | Granite 4.0 MicroIBM Granite | 2.8% | Not benchmarked | $0.112 | |
| 126 | Claude 2RetiredAnthropic | 2.5% | Not benchmarked | $24.00 | |
| 127 | Claude 3 SonnetRetiredAnthropic | 2.5% | Not benchmarked | $15.00 | |
| 128 | Qwen2.5 7B InstructQwen | 2.5% | Not benchmarked | $0.20 | |
| 129 | Claude 3 HaikuRetiredAnthropic | 1.8% | Not benchmarked | $1.25 | |
| 130 | Llama 3.1 8B InstructMeta Llama | 1.7% | Not benchmarked | $0.08 | |
| 131 | Gemma 2 27BGoogle | 1.4% | Not benchmarked | $0.65 | |
| 132 | Llama 3.2 1B InstructMeta Llama | 0.6% | Not benchmarked | $0.201 |
Only models in our catalog are listed, and each appears once with its best published run. 215 rows were read from the source on October 22, 2026, and rows that match no catalog model are left out.