sora 4618c990b1 official swe scorer: PIP_INDEX_URL tuna in eval containers ...

The official eval_script runs pip install -e '.[test]' -- same pypi.org
unreachability as agent containers would burn the 1800s timeout on
network retries. Same tuna mirror injected.

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

2026-09-18 10:45:51 +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

official swe scorer: PIP_INDEX_URL tuna in eval containers

2026-09-18 10:45:51 +00:00

judged.py

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

2026-09-08 05:55:04 +00:00

math.py

Fix numeric normalization in math_equal: strip $, commas, markdown (**), trailing units ('540 meters') — gsm8k 0.45->0.80 on ladder20 cross-check; winogrande cross-scoring 20/20 agreement (delta = generation variance)

2026-08-26 17:15:13 +00:00

mcq.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

qa.py

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

2026-09-08 05:55:04 +00:00