Calibration
Vals MMLU-Pro → GPQA
GPQA is estimated from Vals MMLU-Pro with a linear curve fitted on 24 models measured on both: y = 0.9549·x + 0.0770, R² = 0.77, cross-validated error 1.6 pp. It is used for 21 estimates.
| Estimated model | Vals MMLU-Pro | GPQA | Source |
|---|---|---|---|
| Claude Fable 5.1 | 92.4% | 95.9% | estimated ± 1.6 pp, medium confidence |
| Claude Fable 5 | 91.5% | 95.1% | estimated ± 1.6 pp, medium confidence |
| Gemini 3.7 Flash | 90.1% | 93.7% | estimated ± 1.6 pp, medium confidence |
| Gemini 3.6 Flash | 89.3% | 93.0% | estimated ± 1.6 pp, high confidence |
| Gemini 3 Flash | 88.6% | 92.3% | estimated ± 1.6 pp, high confidence |
| Muse Spark 1.2 | 88.3% | 92.0% | estimated ± 1.6 pp, high confidence |
| Claude Sonnet 5 | 87.5% | 91.3% | estimated ± 1.6 pp, high confidence |
| GLM-5.3 | 86.8% | 90.6% | estimated ± 1.6 pp, high confidence |
| Gemini 3.1 Flash-Lite | 86.2% | 90.0% | estimated ± 1.6 pp, high confidence |
| GLM-5.3-Flash | 86.1% | 89.9% | estimated ± 1.6 pp, high confidence |
| Gemini 3.5 Flash-Lite | 85.8% | 89.6% | estimated ± 1.6 pp, high confidence |
| MiMo-V2.5-Pro | 84.6% | 88.5% | estimated ± 1.6 pp, high confidence |
| MiniMax M3 | 84.2% | 88.1% | estimated ± 1.6 pp, high confidence |
| Qwen3.5 Flash | 84.1% | 88.0% | estimated ± 1.6 pp, high confidence |
| MiMo-V2.5 | 82.9% | 86.9% | estimated ± 1.6 pp, high confidence |
| GLM-4.6 | 82.2% | 86.2% | estimated ± 1.6 pp, high confidence |
| GLM-4.5 | 81.2% | 85.2% | estimated ± 1.6 pp, high confidence |
| Claude Haiku 4.5 | 78.7% | 82.9% | estimated ± 1.6 pp, high confidence |
| Mistral Medium 3.5 128B | 75.3% | 79.6% | estimated ± 1.6 pp, medium confidence |
| Laguna XS.2 | 69.1% | 73.7% | estimated ± 1.6 pp, medium confidence |
| Laguna M.1 | 68.8% | 73.4% | estimated ± 1.6 pp, medium confidence |
Fitted on
| Model | Vals MMLU-Pro | GPQA |
|---|---|---|
| Claude Opus 4.8 | 89.6% | 93.6% |
| Claude Sonnet 4.6 | 87.3% | 89.9% |
| DeepSeek V4 Flash 0731 | 86.2% | 88.1% |
| DeepSeek V4 Pro 0813 | 87.0% | 90.1% |
| Gemini 3.5 Flash | 89.5% | 92.2% |
| GLM-4.7 | 82.7% | 85.7% |
| GLM-5.2 | 86.7% | 91.2% |
| GPT-5.4 mini | 84.6% | 88.0% |
| GPT-5.4 nano | 77.2% | 82.8% |
| GPT-5.5 | 88.1% | 93.6% |
| GPT-5.6 Luna | 86.0% | 92.3% |
| GPT-5.6 Sol | 89.1% | 94.6% |
| GPT-5.6 Terra | 86.7% | 92.9% |
| Grok 4.3 | 85.8% | 90.1% |
| Inkling | 86.3% | 87.9% |
| Inkling-Small | 85.6% | 89.5% |
| Kimi K2.6 | 87.6% | 90.5% |
| Kimi K3 | 88.0% | 93.5% |
| Ling 3.0 Flash | 82.0% | 85.0% |
| Nemotron 3 Ultra | 85.8% | 87.0% |
| Qwen3.6 Plus | 87.7% | 90.4% |
| Qwen3.7 Max | 89.3% | 92.4% |
| Qwen3.8-27B | 84.3% | 89.2% |
| Qwen3.8 Max | 88.6% | 92.6% |