HF Hub Prompt A/B Summary
| Variant | Model | Ch avg (/10) | Cov endpoint | Cov method | Composite | Calls | Tokens |
|---|---|---|---|---|---|---|---|
| baseline | gpt-oss | 10.0 | 1.0 | 1.0 | 1.0 | 93 | 1461966 |
| compact | gpt-oss | 9.583 | 0.9412 | 1.0 | 0.9574 | 58 | 242906 |
Pairwise delta (compact - baseline)
| Model | Δ Ch avg | Δ Cov endpoint | Δ Cov method | Δ Composite | Δ Calls | Δ Tokens |
|---|---|---|---|---|---|---|
| gpt-oss | -0.417 | -0.0588 | +0.0000 | -0.0426 | -35 | -1219060 |