Epoch AI Benchmarking Hub
Ranked among models offered by everyais · 13 models
| Rank | Model | Score |
|---|---|---|
| 1 | GPT-6 Astra Evaluation target / conditions: GPT-6 Astra Measurement date not providedView source ↗ | 169.23 (source scale) |
| 2 | Claude Fable 5 Evaluation target / conditions: Claude Fable 5 Measurement date not providedView source ↗ | 162.9 (source scale) |
| 3 | Claude Fable 5.1 Evaluation target / conditions: Claude Fable 5.1 Measurement date not providedView source ↗ | 162.88 (source scale) |
| 4 | GPT-5.6 Sol Evaluation target / conditions: GPT-5.6 Sol Measurement date not providedView source ↗ | 162.03 (source scale) |
| 5 | GPT-5.6 Terra Evaluation target / conditions: GPT-5.6 Terra Measurement date not providedView source ↗ | 159.18 (source scale) |
| 6 | Claude Opus 4.8 Evaluation target / conditions: Claude Opus 4.8 Measurement date not providedView source ↗ | 158.24 (source scale) |
| 7 | Kimi K3 Evaluation target / conditions: Kimi K3 Measurement date not providedView source ↗ | 157.62 (source scale) |
| 8 | Gemini 3.7 Flash Evaluation target / conditions: Gemini 3.7 Flash Measurement date not providedView source ↗ | 157.32 (source scale) |
| 9 | GPT-5.6 Luna Evaluation target / conditions: GPT-5.6 Luna Measurement date not providedView source ↗ | 156.33 (source scale) |
| 10 | DeepSeek V4 Flash 0731 Evaluation target / conditions: DeepSeek V4 Flash 0731 Measurement date not providedView source ↗ | 154.46 (source scale) |
| 11 | GLM-5.2 Evaluation target / conditions: GLM-5.2 Measurement date not providedView source ↗ | 151.98 (source scale) |
| 12 | GLM-5.3 Flash Evaluation target / conditions: GLM-5.3-Flash Measurement date not providedView source ↗ | 151.64 (source scale) |
| 13 | MiniMax M3 Evaluation target / conditions: MiniMax-M3 Measurement date not providedView source ↗ | 146.57 (source scale) |