quantiles/MMLU-Pro
Viewer • Updated • 12.1k • 45
AI & ML interests
AI evaluation, LLM benchmarking, agent evaluation, reproducible eval workflows, model comparison, regression testing, failure analysis, eval datasets, and open-source developer tooling
Recent Activity
quantiles/gpqa
Viewer • Updated • 1.25k • 60
quantiles/simpleqa-verified
Viewer • Updated • 1k • 14
quantiles/financebench
Viewer • Updated • 150 • 15
quantiles/crows_pairs
Viewer • Updated • 1.51k • 37
quantiles/bold
Viewer • Updated • 7.2k • 20
quantiles/bbq
Viewer • Updated • 117k • 33
quantiles/MedQA-USMLE-4-options
Viewer • Updated • 11.5k • 9
quantiles/medmcqa
Viewer • Updated • 193k • 26
quantiles/PubMedQA
Viewer • Updated • 274k • 24
quantiles/healthbench
Preview • Updated • 7
quantiles/holistic-bias
Viewer • Updated • 491k • 14