Epoch AI Benchmarking Hub
Data source: Epoch AI Benchmarking HubLicense: CC-BY
Synced by EveryAI: This is the sync time, not the measurement date.
| Ranking | EveryAI metrics | ||||||
|---|---|---|---|---|---|---|---|
| # | Model | Score | |||||
| 1 | gpt-6-astraeveryais/gpt-6-astra | 169.23 (source scale) | |||||
| 2 | Claude Fable 5everyais/claude-fable-5 | 162.9 (source scale) | |||||
| 3 | Claude Fable 5.1everyais/claude-fable-5-1 | 162.88 (source scale) | |||||
| 4 | GPT-5.6 Soleveryais/gpt-5-6-sol | 162.03 (source scale) | |||||
| 5 | GPT-5.6 Terraeveryais/gpt-5-6-terra | 159.18 (source scale) | |||||
| 6 | Claude Opus 4.8everyais/claude-opus-4-8 | 158.24 (source scale) | |||||
| 7 | Kimi-K3everyais/kimi-k3 | 157.62 (source scale) | |||||
| 8 | Gemini 3.7 Flasheveryais/gemini-3-7-flash | 157.32 (source scale) | |||||
| 9 | GPT-5.6 Lunaeveryais/gpt-5-6-luna | 156.33 (source scale) | |||||
| 10 | DeepSeek-V4-Flash-0731everyais/deepseek-v4-flash-0731 | 154.46 (source scale) | |||||
| 11 | GLM-5.2everyais/glm-5-2 | 151.98 (source scale) | |||||
| 12 | GLM-5.3-Flasheveryais/glm-5-3-flash | 151.64 (source scale) | |||||
| 13 | MiniMax-M3everyais/minimax-m3 | 146.57 (source scale) | |||||