AIME
Challenging national math exam given to top high-school students
96rows
scoreprimary metric
2026-04-16sampled
Metadata
Metrics
Score, Std. error (lower is better), Latency (lower is better), Cost per test (lower is better)
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 98.125% | Gemini 3.1 Pro Preview google-gemini-3.1-pro-preview | Imported | 2026-04-16 |
| 2 | Muse Spark | 96.875% | — | Imported | 2026-04-16 |
| 3 | GPT 5.2 2025-12-11 | 96.875% | GPT-5.2 openai-gpt-5.2 | Imported | 2026-04-16 |
| 4 | Gemini 3 Pro Preview | 96.68% | Gemini 3 google-gemini-3 | Imported | 2026-04-16 |
| 5 | GPT 5.4 2026-03-05 | 96.667% | GPT-5.4 openai-gpt-5.4 | Imported | 2026-04-16 |
| 6 | Grok 4.20 0309 Reasoning | 96.458% | Grok 4.20 x-ai-grok-4.20 | Imported | 2026-04-16 |
| 7 | Claude Opus 4.7 | 96.25% | Claude Opus 4.7 anthropic-claude-opus-4.7 | Imported | 2026-04-16 |
| 8 | Claude Opus 4.6 Thinking | 95.625% | Claude Opus 4.6 anthropic-claude-opus-4.6 | Imported | 2026-04-16 |
| 9 | Gemini 3 Flash Preview | 95.625% | Gemini 3 Flash Preview google-gemini-3-flash-preview | Imported | 2026-04-16 |
| 10 | Kimi K2.5 Thinking | 95.625% | MoonshotAI: Kimi K2.5 moonshotai-kimi-k2.5 | Imported | 2026-04-16 |
| 11 | GPT 5.4 Mini 2026-03-17 | 95.625% | GPT-5.4 Mini openai-gpt-5.4-mini | Imported | 2026-04-16 |
| 12 | Claude Opus 4.5 20251101 Thinking | 95.417% | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-04-16 |
| 13 | Qwen 3.6 Plus | 94.583% | Qwen3.6 Plus qwen-qwen3.6-plus | Imported | 2026-04-16 |
| 14 | GPT 5.2025-08-07 | 93.374% | GPT-5 openai-gpt-5 | Imported | 2026-04-16 |
| 15 | GPT 5.1 2025-11-13 | 93.333% | GPT-5.1 openai-gpt-5.1 | Imported | 2026-04-16 |
| 16 | GLM 4.7 | 93.333% | GLM 4.7 z-ai-glm-4.7 | Imported | 2026-04-16 |
| 17 | GLM 4.6 | 92.708% | GLM 4.6 z-ai-glm-4.6 | Imported | 2026-04-16 |
| 18 | GPT Oss 120B | 92.598% | gpt-oss-120b openai-gpt-oss-120b | Imported | 2026-04-16 |
| 19 | Qwen 3.5 Flash | 92.5% | Qwen3.5-Flash qwen-qwen3.5-flash-02-23 | Imported | 2026-04-16 |
| 20 | Claude Sonnet 4.6 | 92.292% | Claude Sonnet 4.6 anthropic-claude-sonnet-4.6 | Imported | 2026-04-16 |
| 21 | Grok 4.1 Fast Reasoning | 91.875% | Grok 4.1 Fast x-ai-grok-4.1-fast | Imported | 2026-04-16 |
| 22 | GLM 5.1 Thinking | 91.875% | GLM 5.1 z-ai-glm-5.1 | Imported | 2026-04-16 |
| 23 | GLM 5 Thinking | 91.667% | GLM 5 z-ai-glm-5 | Imported | 2026-04-16 |
| 24 | GPT 5 Mini 2025-08-07 | 91.458% | GPT-5 Mini openai-gpt-5-mini | Imported | 2026-04-16 |
| 25 | Grok 4 Fast Reasoning | 91.25% | Grok 4 Fast x-ai-grok-4-fast | Imported | 2026-04-16 |
| 26 | MiniMax M2.7 | 91.042% | MiniMax M2.7 minimax-minimax-m2.7 | Imported | 2026-04-16 |
| 27 | Grok 4.0709 | 90.556% | Grok 4 x-ai-grok-4 | Imported | 2026-04-16 |
| 28 | MiniMax M2.5 Lightning | 88.75% | — | Imported | 2026-04-16 |
| 29 | GPT 5.4 Nano 2026-03-17 | 88.75% | GPT-5.4 Nano openai-gpt-5.4-nano | Imported | 2026-04-16 |
| 30 | Claude Sonnet 4.5 20250929 Thinking | 88.19% | Claude Sonnet 4.5 anthropic-claude-sonnet-4.5 | Imported | 2026-04-16 |
| 31 | GLM 4.5 | 86.667% | GLM 4.5 z-ai-glm-4.5 | Imported | 2026-04-16 |
| 32 | O3 Mini 2025-01-31 | 86.458% | o3-mini openai-o3-mini | Imported | 2026-04-16 |
| 33 | Qwen 3.5 Plus Thinking | 86.042% | — | Imported | 2026-04-16 |
| 34 | GPT Oss 20B | 86.042% | gpt-oss-20b openai-gpt-oss-20b | Imported | 2026-04-16 |
| 35 | Gemini 2.5 Pro Exp 03 25 | 85.833% | — | Imported | 2026-04-16 |
| 36 | Kimi K2 Thinking | 85.417% | MoonshotAI: Kimi K2 Thinking moonshotai-kimi-k2-thinking | Imported | 2026-04-16 |
| 37 | O3 2025-04-16 | 85.278% | o3 openai-o3 | Imported | 2026-04-16 |
| 38 | Grok 3 Mini Fast High Reasoning | 85% | — | Imported | 2026-04-16 |
| 39 | DeepSeek V3P2 Thinking | 84.583% | — | Imported | 2026-04-16 |
| 40 | Qwen 3 235B A22b | 83.958% | Qwen3 235B A22B qwen-qwen3-235b-a22b | Imported | 2026-04-16 |
| 41 | O4 Mini 2025-04-16 | 83.667% | o4 Mini openai-o4-mini | Imported | 2026-04-16 |
| 42 | Magistral Medium 2509 | 83.542% | — | Imported | 2026-04-16 |
| 43 | Gemini 3.1 Flash Lite Preview | 83.333% | Gemini 3.1 Flash Lite Preview google-gemini-3.1-flash-lite-preview | Imported | 2026-04-16 |
| 44 | Claude Haiku 4.5 20251001 Thinking | 82.708% | Claude Haiku 4.5 anthropic-claude-haiku-4.5 | Imported | 2026-04-16 |
| 45 | GPT 5 Nano 2025-08-07 | 81.181% | GPT-5 Nano openai-gpt-5-nano | Imported | 2026-04-16 |
| 46 | Qwen 3 Max | 81.042% | Qwen3 Max qwen-qwen3-max | Imported | 2026-04-16 |
| 47 | Magistral Small 2509 | 80.679% | — | Imported | 2026-04-16 |
| 48 | Claude Opus 4.1 20250805 Thinking | 78.179% | Claude Opus 4.1 anthropic-claude-opus-4.1 | Imported | 2026-04-16 |
| 49 | MiniMax M2.1 | 77.917% | MiniMax M2.1 minimax-minimax-m2.1 | Imported | 2026-04-16 |
| 50 | Claude Opus 4.5 20251101 | 76.875% | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-04-16 |
| 51 | Claude Sonnet 4.20250514 Thinking | 76.25% | — | Imported | 2026-04-16 |
| 52 | DeepSeek R1 | 73.958% | R1 deepseek-r1 | Imported | 2026-04-16 |
| 53 | O1 2024-12-17 | 71.458% | o1 openai-o1 | Imported | 2026-04-16 |
| 54 | Grok 3 Mini Fast Low Reasoning | 70.625% | — | Imported | 2026-04-16 |
| 55 | DeepSeek V3P2 | 64.792% | — | Imported | 2026-04-16 |
| 56 | Kimi K2 Instruct | 62.708% | MoonshotAI: Kimi K2 0711 moonshotai-kimi-k2 | Imported | 2026-04-16 |
| 57 | Qwen 3 Max Preview | 60.694% | — | Imported | 2026-04-16 |
| 58 | Grok 3 | 58.75% | Grok 3 xaigrok-3 | Imported | 2026-04-16 |
| 59 | Llama 3.3 Nemotron Super 49B V1 42e84561 Thinking | 53.542% | — | Imported | 2026-04-16 |
| 60 | DeepSeek V3 0324 | 52.202% | DeepSeek V3 0324 deepseek-deepseek-chat-v3-0324 | Imported | 2026-04-16 |
| 61 | Gemini 2.5 Flash Preview 09 2025 Thinking | 51.458% | — | Imported | 2026-04-16 |
| 62 | Gemini 2.5 Flash Preview 09 2025 | 49.792% | — | Imported | 2026-04-16 |
| 63 | GPT 4.1 Mini 2025-04-14 | 49.375% | GPT-4.1 Mini openai-gpt-4.1-mini | Imported | 2026-04-16 |
| 64 | Claude 3 7 Sonnet 20250219 Thinking | 44.583% | — | Imported | 2026-04-16 |
| 65 | Claude Opus 4.1 20250805 | 44.236% | Claude Opus 4.1 anthropic-claude-opus-4.1 | Imported | 2026-04-16 |
| 66 | Mistral Large 2512 | 42.917% | Mistral: Mistral Large 3 2512 mistralai-mistral-large-2512 | Imported | 2026-04-16 |
| 67 | Mistral Medium 2505 | 42.292% | — | Imported | 2026-04-16 |
| 68 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | 42.083% | — | Imported | 2026-04-16 |
| 69 | Claude Opus 4.20250514 | 41.25% | Claude Opus 4 anthropic-claude-opus-4 | Imported | 2026-04-16 |
| 70 | GPT 4.1 2025-04-14 | 39.583% | GPT-4.1 openai-gpt-4.1 | Imported | 2026-04-16 |
| 71 | Claude Sonnet 4.20250514 | 38.542% | Claude Sonnet 4 anthropic-claude-sonnet-4 | Imported | 2026-04-16 |
| 72 | Grok 4 Fast Non Reasoning | 33.333% | Grok 4 Fast x-ai-grok-4-fast | Imported | 2026-04-16 |
| 73 | Gemini 2.0 Flash 001 | 29.792% | Gemini 2.0 Flash google-gemini-2.0-flash | Imported | 2026-04-16 |
| 74 | DeepSeek V3 | 27.5% | DeepSeek V3 deepseek-deepseek-chat | Imported | 2026-04-16 |
| 75 | Grok 4.1 Fast Non Reasoning | 27.083% | Grok 4.1 Fast x-ai-grok-4.1-fast | Imported | 2026-04-16 |
| 76 | GPT 4.1 Nano 2025-04-14 | 26.458% | GPT-4.1 Nano openai-gpt-4.1-nano | Imported | 2026-04-16 |
| 77 | Gemini 2.5 Flash Lite Preview 09 2025 | 26.25% | Gemini 2.5 Flash Lite Preview 09-2025 google-gemini-2.5-flash-lite-preview-09-2025 | Imported | 2026-04-16 |
| 78 | Llama4 Maverick Instruct Basic | 25.208% | — | Imported | 2026-04-16 |
| 79 | Claude 3 7 Sonnet 20250219 | 22.292% | Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-04-16 |
| 80 | Llama 4 Scout 17B 16E Instruct | 18.958% | Llama 4 Scout meta-llama-llama-4-scout | Imported | 2026-04-16 |
| 81 | Gemini 1.5 Pro 002 | 18.75% | — | Imported | 2026-04-16 |
| 82 | Gemini 1.5 Flash 002 | 17.292% | — | Imported | 2026-04-16 |
| 83 | Llama 3.3 70B Instruct Turbo | 16.042% | — | Imported | 2026-04-16 |
| 84 | Grok 2.1212 | 15.208% | — | Imported | 2026-04-16 |
| 85 | GPT 4O 2024-08-06 | 13.958% | GPT-4o (2024-08-06) openai-gpt-4o-2024-08-06 | Imported | 2026-04-16 |
| 86 | Command A 03 2025 | 13.333% | Command A cohere-command-a | Imported | 2026-04-16 |
| 87 | GPT 4O 2024-11-20 | 11.875% | GPT-4o (2024-11-20) openai-gpt-4o-2024-11-20 | Imported | 2026-04-16 |
| 88 | GPT 4O Mini 2024-07-18 | 11.458% | GPT-4o-mini (2024-07-18) openai-gpt-4o-mini-2024-07-18 | Imported | 2026-04-16 |
| 89 | Claude 3 5 Sonnet 20241022 | 10% | Claude 3.5 Sonnet anthropic-claude-3.5-sonnet | Imported | 2026-04-16 |
| 90 | Llama 3.3 Nemotron Super 49B V1 42e84561 | 9.375% | — | Imported | 2026-04-16 |
| 91 | Mistral Large 2411 | 9.167% | Mistral Large 2411 mistralai-mistral-large-2411 | Imported | 2026-04-16 |
| 92 | Mistral Small 2402 | 5.625% | — | Imported | 2026-04-16 |
| 93 | Mistral Small 2503 | 3.542% | — | Imported | 2026-04-16 |
| 94 | Claude 3 5 Haiku 20241022 | 3.333% | — | Imported | 2026-04-16 |
| 95 | Jamba Large 1.6 | 0.417% | — | Imported | 2026-04-16 |
| 96 | Jamba Mini 1.6 | 0.417% | — | Imported | 2026-04-16 |
No matching rows.