# MathVision w/ Python → CharXiv w/o tools

Calibration · https://benchgap.net/calibration/mathvisionpython/current/to/charxivnotools/current · data retrieved 2026-11-18

CharXiv w/o tools is estimated from MathVision w/ Python with a Michaelis–Menten + offset curve fitted on 5 models measured on both: y = 0.0000 + 2.0000·x / (1.30412 + x), R² = 0.33, cross-validated error 1.9 pp. It is used for 1 estimate.

| Estimated model | MathVision w/ Python | CharXiv w/o tools | Source |
|---|---|---|---|
| [LongCat-2.5](https://benchgap.net/model/longcat-2-5.md) | 96.5% | 85.1% | estimated ± 1.9 pp, low confidence |

## Fitted on

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