# CharXiv w/o tools → MathVision w/ Python

Calibration · https://benchgap.net/calibration/charxivnotools/current/to/mathvisionpython/current · data retrieved 2026-11-19

MathVision w/ Python is estimated from CharXiv w/o tools with a Michaelis–Menten curve fitted on 5 models measured on both: y = 1.6144·x / (0.57336 + x), R² = 0.43, cross-validated error 1.3 pp. It is used for 1 estimate.

| Estimated model | CharXiv w/o tools | MathVision w/ Python | Source |
|---|---|---|---|
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 86.2% | 97.0% | estimated ± 1.3 pp, low confidence |

## Fitted on

| Model | CharXiv w/o tools | MathVision w/ Python |
|---|---|---|
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 84.8% | 97.8% |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 83.7% | 94.6% |
| [Qwen3.8-Flash-Next](https://benchgap.net/model/qwen3-8-flash-next.md) | 84.6% | 95.7% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 88.4% | 97.7% |
| [Qwen3.8-Omni-Flash](https://benchgap.net/model/qwen3-8-omni-flash.md) | 83.5% | 96.2% |
