Lab Rank | Model Score | Rank Spread | ||
|---|---|---|---|---|
| 1 | Anthropic claude-opus-5.5-max · Proprietary | 1749+30/-30 | 1 | 15 |
| 2 | OpenAI gpt-6-astra-max · Proprietary | 1731+13/-13 | 3 | 15 |
| 3 | Meta muse-spark-1.3-max · Proprietary | 1642+10/-10 | 8 | 69 |
| 4 | Alibaba qwen3.8-max-0902 · Proprietary | 1638+18/-18 | 9 | 612 |
| 5 | DeepSeek deepseek-v4.1-flash-max · MIT | 1609+22/-22 | 12 | 923 |
| 6 | Google gemini-3.7-flash-high · Proprietary | 1603+13/-13 | 14 | 1021 |
| 7 | SpaceXAI grok-4.6-high · Proprietary | 1601+12/-12 | 15 | 1122 |
| 8 | Xiaomi mimo-v2.6-flash · MIT | 1597+14/-14 | 17 | 1124 |
| 9 | Z.ai glm-5.3-flash · MIT | 1581+10/-10 | 20 | 1326 |
| 10 | Moonshot kimi-k3-max · Kimi K3 license | 1579+11/-11 | 21 | 1427 |
| 11 | StepFun step-5-preview-high · Proprietary | 1541+15/-15 | 30 | 2641 |
| 12 | Bytedance seed-2.1-pro-preview · Proprietary | 1510+10/-10 | 42 | 3745 |
| 13 | MiniMax minimax-m3 · MiniMax Community License | 1473+9/-9 | 47 | 4548 |
| 14 | Thinky Inkling Small · Apache 2.0 | 1410+19/-19 | 59 | 5259 |
| 15 | Mistral mistral-large-3 · Apache 2.0 | 1362+17/-17 | 61 | 6063 |