Calibration
CritPt → BioBasicsBench
BioBasicsBench is estimated from CritPt with a offset logistic curve fitted on 7 models measured on both: y = 0.3393 + (0.5840 − 0.3393) / (1 + exp(−200.00·(x − 0.2841))), R² = 0.78, cross-validated error 10.7 pp. It is used for 38 estimates.
| Estimated model | CritPt | BioBasicsBench | Source |
|---|---|---|---|
| Sage-A1.5 | 20.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Beam 1.0 501B-A23B FP8 | 17.4% | 33.9% | estimated ± 10.7 pp, low confidence |
| Beam 1.0 501B-A23B NVFP4 | 15.4% | 33.9% | estimated ± 10.7 pp, low confidence |
| Celeris-1 | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Exaone 4.0 1.2B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Exaone 4.0 32B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Gemma 4 12B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Gemma 4 26B A4B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Gemma 4 E2B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| GPT-OSS 20B | 1.4% | 33.9% | estimated ± 10.7 pp, low confidence |
| Granite-4.0-350M | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Granite-4.0-H-1B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Granite-4.0-H-350M | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Granite 4.2 30B | 0.3% | 33.9% | estimated ± 10.7 pp, low confidence |
| LFM2.5-2.6B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| LFM2.5-8B-A1B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| LFM2.5-VL-1.6B-Extract | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Llama 3.1 405B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Llama 3.1 70B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Llama 3.3 70B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Llama 4 Maverick | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Llama 4 Scout | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| MiniCPM5-2B | 0.3% | 33.9% | estimated ± 10.7 pp, low confidence |
| Nemotron 3 Nano 30B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Nemotron 3 Nano Omni 30B A3B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Nemotron Ultra 253B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| o3 | 1.1% | 33.9% | estimated ± 10.7 pp, low confidence |
| Phi-4 | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Phi-4-reasoning | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Quasar 438B | 9.4% | 33.9% | estimated ± 10.7 pp, low confidence |
| Qwen3.5-4B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Qwen3-Omni-30B-A3B-Instruct | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Qwen3-Omni-30B-A3B-Thinking | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Sarvam 105B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
| Sarvam 30B | 0.3% | 33.9% | estimated ± 10.7 pp, low confidence |
| Trinity-Large-Preview | 0.9% | 33.9% | estimated ± 10.7 pp, low confidence |
| Trinity-Large-Thinking | 0.9% | 33.9% | estimated ± 10.7 pp, low confidence |
| Ultravox v0.6 Llama 3.3 70B | 0.0% | 33.9% | estimated ± 10.7 pp, low confidence |
Fitted on
| Model | CritPt | BioBasicsBench |
|---|---|---|
| GPT-5.2 | 11.6% | 31.2% |
| GPT-5.4 | 23.4% | 33.2% |
| GPT-5.5 | 27.1% | 35.4% |
| GPT-5.6 Sol | 32.3% | 45.6% |
| GPT-6.1 Sol | 31.7% | 62.6% |
| GPT-6 Astra | 31.7% | 67.0% |
| GPT-6 Luna | 19.4% | 37.6% |