lighteval
Use `n=16` samples to estimate `pass@1` for AIME benchmarks
#661
Merged
Overview
Commits
2
Changes
View On GitHub

Use `n=16` samples to estimate `pass@1` for AIME benchmarks #661

lewtun merged 2 commits into main from aime-pass@k
lewtun
lewtun Use n=16 samples to estimate pass@1 for AIME benchmarks
7c7c28a0
lewtun Remove other metrics
35058768
lewtun lewtun requested a review from NathanHB NathanHB 332 days ago
lewtun lewtun requested a review from clefourrier clefourrier 332 days ago
HuggingFaceDocBuilderDev
clefourrier
clefourrier approved these changes on 2025-04-07
clefourrier
lewtun
lewtun
clefourrier
lewtun lewtun merged f3639c67 into main 331 days ago
NathanHB NathanHB added task-update
CurryxIaoHu
lewtun
Cppowboy
lewtun

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
task-update
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum