Calibration
MCP Atlas → APEX-Agents-AA
APEX-Agents-AA is estimated from MCP Atlas with a linear curve fitted on 13 models measured on both: y = 0.4758·x + -0.0158, R² = 0.74, cross-validated error 5.7 pp. It is used for 7 estimates.
| Estimated model | MCP Atlas | APEX-Agents-AA | Source |
|---|---|---|---|
| Kimi K2.7 Code | 76.0% | 34.6% | estimated ± 5.7 pp, medium confidence |
| LLaDA2.2-flash | 46.2% | 20.4% | estimated ± 5.7 pp, medium confidence |
| Muse Glimmer 30B | 75.5% | 34.3% | estimated ± 5.7 pp, medium confidence |
| Qwen3.6-35B-A3B | 62.8% | 28.3% | estimated ± 5.7 pp, medium confidence |
| Qwen3.6 Plus | 48.2% | 21.4% | estimated ± 5.7 pp, medium confidence |
| Qwen3.7 Max | 76.4% | 34.8% | estimated ± 5.7 pp, medium confidence |
| Solar Open 2 | 58.2% | 26.1% | estimated ± 5.7 pp, medium confidence |