Calibration
ZeroBench → MathVision
MathVision is estimated from ZeroBench with a Hill curve fitted on 5 models measured on both: y = 0.8941 + (1.2000 − 0.8941)·x^6.00 / (0.30847^6.00 + x^6.00), R² = 0.59, cross-validated error 2.7 pp. It is used for 2 estimates.
| Estimated model | ZeroBench | MathVision | Source |
|---|---|---|---|
| Gemini 3.1 Pro | 29.0% | 100.0% | estimated ± 2.7 pp, low confidence |
| Muse Spark | 33.0% | 100.0% | estimated ± 2.7 pp, low confidence |
Fitted on
| Model | ZeroBench | MathVision |
|---|---|---|
| dots3-note Preview | 19.0% | 87.7% |
| Kimi K3 | 23.0% | 94.3% |
| Qwen3.8 Max | 24.0% | 95.2% |
| Seed 2.1 Pro | 18.0% | 92.6% |
| Seed 2.1 Turbo | 11.0% | 90.1% |