Evaluation sources/MCP Atlas
ObservingProfessional work
MCP Atlas
Scale AI · Public model evaluation results from MCP Atlas.
Model results from this source
| Muse Spark 1.1 | 88.1 | 88.1 | 2026-11-05 |
| Muse Spark 1.1 | 88.1 | 88.1 | 2026-07-09 |
| Muse Spark 1.1 | 88.1 | 88.1 | 2026-10-18 |
| Claude Opus 5 | 85.8 | 85.8 | 2026-10-18 |
| Claude Opus 5 | 85.8 | 85.8 | 2026-11-05 |
| GLM 5.3 | 84.2 | 84.2 | 2026-11-05 |
| GLM 5.3 | 84.2 | 84.2 | 2026-10-18 |
| Claude Fable 5 | 83.3 | 83.3 | 2026-10-18 |
| Claude Fable 5 | 83.3 | 83.3 | 2026-11-05 |
| Kimi K3 | 82.3 | 82.3 | 2026-10-18 |
| Kimi K3 | 82.3 | 82.3 | 2026-11-05 |
| Claude Opus 4.8 | 82.2 | 82.2 | 2026-11-05 |
| Claude Opus 4.8 | 82.2 | 82.2 | 2026-10-18 |
| GPT-5.6 Sol | 81.8 | 81.8 | 2026-11-05 |
| GPT-5.6 Sol | 81.8 | 81.8 | 2026-10-18 |
| Inkling Small | 79.2 | 79.2 | 2026-11-05 |
| Inkling Small | 79.2 | 79.2 | 2026-10-18 |
| Claude Opus 4.7 | 79.1 | 79.1 | 2026-11-05 |
| Claude Opus 4.7 | 79.1 | 79.1 | 2026-10-18 |
| Gemini 3.1 Pro Preview | 78.2 | 78.2 | 2026-11-05 |
| Gemini 3.1 Pro Preview | 78.2 | 78.2 | 2026-05-19 |
| Gemini 3.1 Pro Preview | 78.2 | 78.2 | 2026-10-18 |
| Claude Opus 4.6 | 76.8 | 76.8 | 2026-10-18 |
| Claude Opus 4.6 | 76.8 | 76.8 | 2026-11-05 |
| Qwen3.7 Max | 76.4 | 76.4 | 2026-05-19 |
| Kimi K2.7 Code | 76 | 76.0 | 2026-06-12 |
| Inkling | 76 | 76.0 | 2026-11-05 |
| Inkling | 76 | 76.0 | 2026-10-18 |
| GPT-5.5 | 75.3 | 75.3 | 2026-04-23 |
| GPT-5.5 | 75.3 | 75.3 | 2026-10-18 |
| GPT-5.5 | 75.3 | 75.3 | 2026-11-05 |
| MiniMax-M3 | 74.2 | 74.2 | 2026-06-01 |
| GPT-5.4 | 70.6 | 70.6 | 2026-11-05 |
| GPT-5.4 | 70.6 | 70.6 | 2026-10-18 |
| Gemini 3 Pro Preview | 70.3 | 70.3 | 2026-11-05 |
| Gemini 3 Pro Preview | 70.3 | 70.3 | 2026-10-18 |
| Claude Opus 4.5 | 69.8 | 69.8 | 2026-11-05 |
| Claude Opus 4.5 | 69.8 | 69.8 | 2026-10-18 |
| Claude Sonnet 4.6 | 69.5 | 69.5 | 2026-10-18 |
| Claude Sonnet 4.6 | 69.5 | 69.5 | 2026-11-05 |
| GPT-5.2 | 67.6 | 67.6 | 2026-11-05 |
| GPT-5.2 | 67.6 | 67.6 | 2026-10-18 |
| Gemini 3 Flash Preview | 62 | 62.0 | 2026-11-05 |
| Gemini 3 Flash Preview | 62 | 62.0 | 2026-10-18 |
| Claude Sonnet 4.5 | 59.5 | 59.5 | 2026-11-05 |
| Claude Sonnet 4.5 | 59.5 | 59.5 | 2026-10-18 |
| Gemini 3.1 Flash Lite | 57.1 | 57.1 | 2026-10-18 |
| Gemini 3.1 Flash Lite | 57.1 | 57.1 | 2026-11-05 |
| GPT-5.4 mini | 56.7 | 56.7 | 2026-10-18 |
| GPT-5.4 mini | 56.7 | 56.7 | 2026-11-05 |
| o3-pro | 44.5 | 44.5 | 2026-10-18 |
| o3-pro | 44.5 | 44.5 | 2026-11-05 |
| Claude Haiku 4.5 | 40.2 | 40.2 | 2026-10-18 |
| Claude Haiku 4.5 | 40.2 | 40.2 | 2026-11-05 |