EvalHarness

History

sora 014e8bcd9b swe scorer: metadata from env_state (positional pair misalign fix)

sample.metadata vs env_state mismatch confirmed: sample[0] said
astropy-12907 while the paired prediction held 13453's test_patch --
make_test_spec built the eval_script for the WRONG bug, scoring real
patches against wrong tests (0/10 despite manual verification that
the patches are correct). The env_state IS the actual instance the
agent ran; it takes priority, sample.metadata fills gaps.

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

2026-09-18 15:28:05 +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

swe scorer: metadata from env_state (positional pair misalign fix)

2026-09-18 15:28:05 +00:00

judged.py

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