# V* → We-Math

Calibration · https://benchgap.net/calibration/1661 · data retrieved 2026-10-29

We-Math is estimated from V* with a linear curve fitted on 5 models measured on both: y = 0.5159·x + 0.3586, R² = 0.41, cross-validated error 8.5 pp. It is used for 0 estimates.

## Fitted on

| Model | V* | We-Math |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 67.0% | 70.0% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 88.0% | 86.9% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 75.9% | 79.0% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 86.4% | 68.6% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 95.8% | 87.9% |