evalstone/bash/run_full.py
2026-07-21 09:32:49 +00:00

75 lines
1.4 KiB
Python

#!/usr/bin/env python3
"""
Full evaluation suite: ~3-5 days
Runs all benchmarks with full datasets and multiple runs for stability.
Use --limit none (default) for the complete evaluation.
"""
from pathlib import Path
import sys
sys.path.insert(0, str(Path(__file__).parent))
import run as run_module
# Use the default full configuration from run.py
# (already ordered by estimated runtime)
run_module._multi_run_order = [
'humaneval',
'live_code_bench',
'aime26',
'aime24',
'aime25',
'gpqa_diamond',
'imo_answerbench',
'hmmt26',
]
run_module._single_run_order = [
'arc',
'bfcl_v3',
'winogrande',
'competition_math',
'gsm8k',
'hellaswag',
'bigcodebench',
'drop',
'bbh',
'openai_mrcr',
'longbench_v2',
'mmlu',
'cmmlu',
'super_gpqa',
'simple_qa',
'mmlu_pro',
'hle',
'trivia_qa',
]
run_module._agent_order = [
'tau2_bench',
'general_fc',
]
run_module.DATASETS = (
run_module._multi_run_order
+ run_module._single_run_order
+ run_module._agent_order
)
# Full: many runs for statistical stability
run_module.MULTI_RUN_CONFIG = {
'aime24': 12,
'aime25': 12,
'aime26': 12,
'hmmt26': 12,
'live_code_bench': 5,
'imo_answerbench': 4,
'humaneval': 3,
'gpqa_diamond': 2,
}
if __name__ == '__main__':
print('Full benchmarks:', run_module.DATASETS)
print('Estimated time: ~3-5 days with --limit none')
run_module.main()