Calibration
MCP Atlas → MCP-Tasks
MCP-Tasks is estimated from MCP Atlas with a Hill curve fitted on 5 models measured on both: y = 0.5077 + (0.7722 − 0.5077)·x^6.00 / (0.33665^6.00 + x^6.00), R² = 1.00, cross-validated error 0.6 pp. It is used for 34 estimates.
| Estimated model | MCP Atlas | MCP-Tasks | Source |
|---|---|---|---|
| Claude Opus 4.7 (Adaptive) | 77.3% | 77.0% | estimated ± 0.6 pp, low confidence |
| Claude Opus 4.8 | 82.2% | 77.1% | estimated ± 0.6 pp, low confidence |
| Claude Opus 5 | 85.8% | 77.1% | estimated ± 0.6 pp, low confidence |
| DeepSeek V4 Flash 0731 | 69.0% | 76.9% | estimated ± 0.6 pp, low confidence |
| DeepSeek V4 Pro 0813 | 73.6% | 77.0% | estimated ± 0.6 pp, low confidence |
| Gemini 3.5 Flash | 83.6% | 77.1% | estimated ± 0.6 pp, low confidence |
| GLM-5.1 | 71.8% | 76.9% | estimated ± 0.6 pp, low confidence |
| GLM-5.2 | 76.8% | 77.0% | estimated ± 0.6 pp, low confidence |
| GPT-5.4 | 70.6% | 76.9% | estimated ± 0.6 pp, low confidence |
| GPT-5.4 mini | 57.7% | 76.2% | estimated ± 0.6 pp, low confidence |
| GPT-5.4 nano | 56.1% | 76.0% | estimated ± 0.6 pp, low confidence |
| GPT-5.5 | 75.3% | 77.0% | estimated ± 0.6 pp, low confidence |
| Hy4 preview | 83.7% | 77.1% | estimated ± 0.6 pp, low confidence |
| Inkling | 74.1% | 77.0% | estimated ± 0.6 pp, low confidence |
| Inkling-Small | 79.6% | 77.1% | estimated ± 0.6 pp, low confidence |
| Kimi K2.6 | 55.9% | 76.0% | estimated ± 0.6 pp, low confidence |
| Kimi K2.7 Code | 76.0% | 77.0% | estimated ± 0.6 pp, low confidence |
| Kimi K3 | 84.2% | 77.1% | estimated ± 0.6 pp, low confidence |
| Ling 3.0 Flash | 65.5% | 76.7% | estimated ± 0.6 pp, low confidence |
| LLaDA2.2-flash | 46.2% | 73.8% | estimated ± 0.6 pp, medium confidence |
| LongCat-Flash-Lite-Sparse | 45.6% | 73.5% | estimated ± 0.6 pp, medium confidence |
| MiniMax M3 | 74.2% | 77.0% | estimated ± 0.6 pp, low confidence |
| Muse Glimmer 30B | 75.5% | 77.0% | estimated ± 0.6 pp, low confidence |
| Muse Spark 1.1 | 88.1% | 77.1% | estimated ± 0.6 pp, low confidence |
| Ornith-1.5-35B-A3B | 70.2% | 76.9% | estimated ± 0.6 pp, low confidence |
| Ornith-1.5-397B | 80.0% | 77.1% | estimated ± 0.6 pp, low confidence |
| Ornith-1.5-9B | 54.2% | 75.8% | estimated ± 0.6 pp, low confidence |
| Qwen3.6-35B-A3B | 62.8% | 76.6% | estimated ± 0.6 pp, low confidence |
| Qwen3.7 Max | 76.4% | 77.0% | estimated ± 0.6 pp, low confidence |
| Qwen3.7 Plus | 73.2% | 77.0% | estimated ± 0.6 pp, low confidence |
| Beam | 78.7% | 77.1% | estimated ± 0.6 pp, low confidence |
| Solar Open 2 | 58.2% | 76.3% | estimated ± 0.6 pp, low confidence |
| Solar Pro 4 | 61.4% | 76.5% | estimated ± 0.6 pp, low confidence |
| Step 5 Preview | 85.6% | 77.1% | estimated ± 0.6 pp, low confidence |