# Terminal-Bench 3.0 → Terminal-Bench 2.1 (Vals AI)

Calibration · https://benchgap.net/calibration/1502 · data retrieved 2026-10-29

Terminal-Bench 2.1 (Vals AI) is estimated from Terminal-Bench 3.0 with a linear curve fitted on 11 models measured on both: y = 0.4268·x + 0.6738, R² = 0.65, cross-validated error 4.0 pp. It is used for 0 estimates.

## Fitted on

| Model | Terminal-Bench 3.0 | Terminal-Bench 2.1 (Vals AI) |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 34.1% | 80.5% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 21.1% | 71.9% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 42.7% | 84.6% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 14.6% | 74.5% |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 14.9% | 77.5% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 4.6% | 67.8% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 14.3% | 79.0% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 34.6% | 85.8% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 20.8% | 77.5% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 15.7% | 67.8% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 26.5% | 78.3% |