Calibration
HMMT Feb 2026 → HMMT Feb 2025
HMMT Feb 2025 is estimated from HMMT Feb 2026 with a Michaelis–Menten curve fitted on 7 models measured on both: y = 2.0000·x / (0.95975 + x), R² = 0.47, cross-validated error 1.8 pp. It is used for 14 estimates.
| Estimated model | HMMT Feb 2026 | HMMT Feb 2025 | Source |
|---|---|---|---|
| DeepSeek V4 Flash 0731 | 94.8% | 99.4% | estimated ± 1.8 pp, low confidence |
| DeepSeek V4 Pro 0813 | 95.2% | 99.6% | estimated ± 1.8 pp, low confidence |
| Inkling-Small | 90.2% | 96.9% | estimated ± 1.8 pp, low confidence |
| K-EXAONE 2.0 | 78.4% | 89.9% | estimated ± 1.8 pp, low confidence |
| Kimi K2.6 | 92.7% | 98.3% | estimated ± 1.8 pp, low confidence |
| Ling 3.0 Flash | 87.0% | 95.1% | estimated ± 1.8 pp, low confidence |
| LongCat-Flash-Lite-Sparse | 40.5% | 59.4% | estimated ± 1.8 pp, low confidence |
| MAI-Thinking-1 | 84.9% | 93.9% | estimated ± 1.8 pp, low confidence |
| MiniCPM5-1B | 25.8% | 42.3% | estimated ± 1.8 pp, low confidence |
| MiniCPM5-2B | 63.8% | 79.9% | estimated ± 1.8 pp, low confidence |
| Qwen3.7 Max | 97.1% | 100.0% | estimated ± 1.8 pp, low confidence |
| Qwen3.7 Plus | 92.9% | 98.4% | estimated ± 1.8 pp, low confidence |
| Solar Open 2 | 93.9% | 98.9% | estimated ± 1.8 pp, low confidence |
| ZAYA1-8B | 71.6% | 85.5% | estimated ± 1.8 pp, low confidence |