# τ³-bench results → PinchBench

Calibration · https://benchgap.net/calibration/1497 · data retrieved 2026-10-29

PinchBench is estimated from τ³-bench results with a Michaelis–Menten + offset curve fitted on 7 models measured on both: y = 0.0000 + 0.9691·x / (0.01787 + x), R² = 0.83, cross-validated error 5.5 pp. It is used for 8 estimates.

| Estimated model | τ³-bench results | PinchBench | Source |
|---|---|---|---|
| [Mercury 2.5](https://benchgap.net/model/mercury-2-5.md) | 96.0% | 95.1% | estimated ± 5.5 pp, low confidence |
| [Mistral Medium 3.5 128B](https://benchgap.net/model/mistral-medium-3-5-128b.md) | 91.4% | 95.0% | estimated ± 5.5 pp, low confidence |
| [MiMo-V2.5-Pro](https://benchgap.net/model/mimo-v2-5-pro.md) | 72.9% | 94.6% | estimated ± 5.5 pp, low confidence |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 70.7% | 94.5% | estimated ± 5.5 pp, low confidence |
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 70.2% | 94.5% | estimated ± 5.5 pp, low confidence |
| [MiniMax M2.7](https://benchgap.net/model/minimax-m2-7.md) | 67.6% | 94.4% | estimated ± 5.5 pp, low confidence |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 67.2% | 94.4% | estimated ± 5.5 pp, low confidence |
| [Mercury 3](https://benchgap.net/model/mercury-3.md) | 30.2% | 91.5% | estimated ± 5.5 pp, low confidence |

## Fitted on

| Model | τ³-bench results | PinchBench |
|---|---|---|
| [LFM2.5-2.6B](https://benchgap.net/model/lfm2-5-2-6b.md) | 5.7% | 68.2% |
| [LFM2.5-24B-A2B](https://benchgap.net/model/lfm2-5-24b-a2b.md) | 8.0% | 83.2% |
| [Nemotron 3.5 Bolt 74B-A9B](https://benchgap.net/model/nemotron-3-5-bolt-74b-a9b.md) | 17.0% | 87.8% |
| [Nemotron 3.5 Bolt 74B-A9B BF16](https://benchgap.net/model/nemotron-3-5-bolt-74b-a9b-bf16.md) | 17.0% | 90.4% |
| [Nemotron 3.5 Lightning 30B A3B NVFP4](https://benchgap.net/model/nemotron-3-5-lightning-30b-a3b-nvfp4.md) | 9.5% | 83.4% |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 70.9% | 90.0% |
| [Pokee-Isaac 28B](https://benchgap.net/model/pokee-isaac-28b.md) | 66.2% | 95.7% |