# VITA-Bench → Claw-Eval

Calibration · https://benchgap.net/calibration/1651 · data retrieved 2026-10-29

Claw-Eval is estimated from VITA-Bench with a Hill curve fitted on 7 models measured on both: y = 0.0000 + (0.6308 − 0.0000)·x^6.00 / (0.16500^6.00 + x^6.00), R² = 0.77, cross-validated error 7.1 pp. It is used for 3 estimates.

| Estimated model | VITA-Bench | Claw-Eval | Source |
|---|---|---|---|
| [Sage-A1.5](https://benchgap.net/model/sage-a1-5.md) | 45.4% | 62.9% | estimated ± 7.1 pp, low confidence |
| [Agents-A1-4B](https://benchgap.net/model/agents-a1-4b.md) | 40.3% | 62.8% | estimated ± 7.1 pp, low confidence |
| [Agents-A1](https://benchgap.net/model/agents-a1.md) | 38.8% | 62.7% | estimated ± 7.1 pp, low confidence |

## Fitted on

| Model | VITA-Bench | Claw-Eval |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 23.3% | 59.6% |
| [DeepSeek V3.2](https://benchgap.net/model/deepseek-v3-2.md) | 18.5% | 40.2% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 43.7% | 56.8% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 35.6% | 68.7% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 44.3% | 58.8% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 47.9% | 65.2% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 45.6% | 62.7% |