hf-papers / docs /hf_hub_prompt_ab /prompt_ab_summary.md
evalstate's picture
evalstate HF Staff
sync: promote hf_hub_community prompt v3 + add prompt/coverage harness
bba4fab verified

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