EvalHarness

History

sora fd7e1af3a4 bigcodebench: override the image ENTRYPOINT so our runner executes

The official image's ENTRYPOINT is 'python3 -m bigcodebench.evaluate'
-- our 'python /work/main.py' runner was swallowed as CLI args and the
official evaluator died on 'No samples provided'. execution scorer now
accepts entrypoint= and docker exec passes --entrypoint; the BCB recipe
sets entrypoint python3. Also swept 7 leaked eh-exec containers (the
--rm path never fires when our timeout kills the CLI first).

Co-Authored-By: Claude <noreply@anthropic.com>

2026-09-17 03:05:13 +00:00

__init__.py

Add evaluation layer + visualization: extract/score/aggregate plugins, 28 recipes, official-aligned scorers (PRM800K math, DROP Hungarian EM/F1, SimpleQA A/B/C judge), report artifacts, console renderers, CLI eval/viz, regression tests

2026-08-24 06:09:38 +00:00

_simpleqa_grader.txt

Paper-faithful eval: P1 logprob scoring (completions_echo + chat_first_token fallback, sglang top_logprobs parser), few_shot_num dataset defaults (mmlu5/cmmlu5/mmlu_pro5/gsm8k4/math4/drop3), official BBH 3-shot CoT vendored, strict_letter default prompt (evalscope parity), official simpleqa grader prompt

2026-08-25 02:21:59 +00:00

agent.py

bigcodebench: override the image ENTRYPOINT so our runner executes

2026-09-17 03:05:13 +00:00

judged.py

dp4-flash 28-bench alignment: renderer plugin layer, exec_workers, gen_profiles, AIMD pool, BCB/LCB/bfcl/gfc judge fixes