# Full-dataset sample counts per benchmark (fallback for the Run Plan
# when the dataset is not cached locally yet -- harvested from real runs;
# update when a benchmark's source changes).
humaneval: 164
aime24: 30
aime25: 30
aime26: 30
hmmt26: 30
gpqa_diamond: 198
mmlu: 285
mmlu_pro: 12032
cmmlu: 11528
gsm8k: 1319
arc: 2376
hellaswag: 10042
winogrande: 1267
drop: 9535
longbench_v2: 503
live_code_bench: 1055
bigcodebench: 1140
trivia_qa: 17944
simple_qa: 4326
hle: 2500
imo_answerbench: 89
openai_mrcr: 1300
bfcl_v3: 2000
general_fc: 400
tau2_bench: 184
competition_math: 5000
swe_bench_verified: 500