# We-Math → CharXiv

Calibration · https://benchgap.net/calibration/1667 · data retrieved 2026-10-29

CharXiv is estimated from We-Math with a Michaelis–Menten curve fitted on 5 models measured on both: y = 2.0000·x / (1.27277 + x), R² = 0.66, cross-validated error 6.3 pp. It is used for 0 estimates.

## Fitted on

| Model | We-Math | CharXiv |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 70.0% | 68.5% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 86.9% | 81.4% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 79.0% | 82.1% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 84.7% | 77.5% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 87.9% | 80.8% |