Calibration
GPQA → CritPt
CritPt is estimated from GPQA with a offset logistic curve fitted on 84 models measured on both: y = 0.0033 + (0.4421 − 0.0033) / (1 + exp(−40.35·(x − 0.9360))), R² = 0.82, cross-validated error 4.0 pp. It is used for 42 estimates.
| Estimated model | GPQA | CritPt | Source |
|---|---|---|---|
| GPT-6.2 Astra | 97.0% | 35.3% | estimated ± 4.0 pp, medium confidence |
| GPT-6.2 Sol | 96.0% | 32.1% | estimated ± 4.0 pp, high confidence |
| Sakana Fugu | 95.5% | 30.3% | estimated ± 4.0 pp, high confidence |
| Sakana Fugu-Ultra | 95.5% | 30.3% | estimated ± 4.0 pp, high confidence |
| Claude Mythos 5 | 94.1% | 24.5% | estimated ± 4.0 pp, high confidence |
| Ornith-1.5-397B | 92.8% | 18.8% | estimated ± 4.0 pp, high confidence |
| Qwen3.8 Max | 92.6% | 17.9% | estimated ± 4.0 pp, high confidence |
| Qwen3.8-Omni-Flash | 91.0% | 11.7% | estimated ± 4.0 pp, high confidence |
| Ornith-1.5-35B-A3B | 89.2% | 6.7% | estimated ± 4.0 pp, high confidence |
| Ornith-1.5-9B | 86.4% | 2.6% | estimated ± 4.0 pp, high confidence |
| Ternary Bonsai 2 27B | 85.8% | 2.1% | estimated ± 4.0 pp, high confidence |
| MAI-Thinking-1 | 84.2% | 1.3% | estimated ± 4.0 pp, high confidence |
| Ling 3.0 Flash FP8 | 84.0% | 1.2% | estimated ± 4.0 pp, high confidence |
| Claude Sonnet 4.5 | 83.4% | 1.0% | estimated ± 4.0 pp, high confidence |
| DeepSeek-R1-0528 | 81.0% | 0.6% | estimated ± 4.0 pp, high confidence |
| Grok 3 Mini | 80.3% | 0.5% | estimated ± 4.0 pp, high confidence |
| Nemotron 3 Super 100B | 79.2% | 0.5% | estimated ± 4.0 pp, high confidence |
| o1-pro | 79.0% | 0.5% | estimated ± 4.0 pp, high confidence |
| Qwen3 235B 2507 | 77.5% | 0.4% | estimated ± 4.0 pp, high confidence |
| Grok 3 [Beta] | 75.4% | 0.4% | estimated ± 4.0 pp, high confidence |
| GLM-4.7-Flash | 75.2% | 0.4% | estimated ± 4.0 pp, high confidence |
| LFM2.5-24B-A2B | 74.4% | 0.3% | estimated ± 4.0 pp, high confidence |
| ZAYA1-8B | 71.0% | 0.3% | estimated ± 4.0 pp, high confidence |
| Spark-X2.6-4B | 69.9% | 0.3% | estimated ± 4.0 pp, high confidence |
| GPT-4.5 | 69.5% | 0.3% | estimated ± 4.0 pp, high confidence |
| Phi-4-reasoning-plus | 68.9% | 0.3% | estimated ± 4.0 pp, high confidence |
| LFM3-1.7B | 63.4% | 0.3% | estimated ± 4.0 pp, high confidence |
| Qwen2.5-Max | 60.1% | 0.3% | estimated ± 4.0 pp, high confidence |
| Claude 3.5 Sonnet | 59.4% | 0.3% | estimated ± 4.0 pp, high confidence |
| Mellum2-12B-A2.5B-Thinking | 57.6% | 0.3% | estimated ± 4.0 pp, high confidence |
| ZAYA1-74B-Preview | 57.3% | 0.3% | estimated ± 4.0 pp, high confidence |
| Grok 2 | 56.0% | 0.3% | estimated ± 4.0 pp, high confidence |
| Grok 2 mini | 51.0% | 0.3% | estimated ± 4.0 pp, high confidence |
| Gemini 2.0 Flash-Lite | 50.5% | 0.3% | estimated ± 4.0 pp, high confidence |
| Qwen2.5-VL-32B | 46.0% | 0.3% | estimated ± 4.0 pp, high confidence |
| Soofi S 30B-A3B | 43.4% | 0.3% | estimated ± 4.0 pp, high confidence |
| Mellum2-12B-A2.5B-Instruct | 40.9% | 0.3% | estimated ± 4.0 pp, high confidence |
| LFM2.5-350M | 30.6% | 0.3% | estimated ± 4.0 pp, high confidence |
| Phi-3.5-mini | 30.4% | 0.3% | estimated ± 4.0 pp, high confidence |
| Granite-4.0-1B | 29.9% | 0.3% | estimated ± 4.0 pp, high confidence |
| LFM2.5-VL-450M | 25.7% | 0.3% | estimated ± 4.0 pp, high confidence |
| LFM2.5-230M | 25.4% | 0.3% | estimated ± 4.0 pp, high confidence |