# CursorBench 3.2 → ProgramBench

Calibration · https://benchgap.net/calibration/cursor-bench32/current/to/programbench/current · data retrieved 2026-11-18

ProgramBench is estimated from CursorBench 3.2 with a Hill curve fitted on 5 models measured on both: y = 0.1578 + (1.0080 − 0.1578)·x^6.00 / (0.51881^6.00 + x^6.00), R² = 0.97, cross-validated error 6.0 pp. It is used for 9 estimates.

| Estimated model | CursorBench 3.2 | ProgramBench | Source |
|---|---|---|---|
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 70.8% | 89.4% | estimated ± 6.0 pp, low confidence |
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 70.5% | 89.1% | estimated ± 6.0 pp, low confidence |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 69.2% | 88.0% | estimated ± 6.0 pp, low confidence |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 64.9% | 83.2% | estimated ± 6.0 pp, low confidence |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 61.5% | 78.3% | estimated ± 6.0 pp, low confidence |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 61.1% | 77.6% | estimated ± 6.0 pp, low confidence |
| [Composer 2.5](https://benchgap.net/model/composer-2-5.md) | 56.1% | 68.1% | estimated ± 6.0 pp, low confidence |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 53.5% | 62.2% | estimated ± 6.0 pp, low confidence |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 48.8% | 50.6% | estimated ± 6.0 pp, low confidence |

## Fitted on

| Model | CursorBench 3.2 | ProgramBench |
|---|---|---|
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 73.4% | 87.6% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 70.0% | 93.0% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 55.0% | 63.7% |
| [Kimi K2.7 Code](https://benchgap.net/model/kimi-k2-7-code.md) | 49.7% | 53.6% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 60.8% | 77.8% |
