OpenCompass/opencompass/configs/datasets/aime2024
Dongsheng Zhu 465e93e10e
[Update] Academic bench llm judge update (#1876)
* BigCodeBench update

* update LCBench

* update LCBench 2

* update code

* academicBench update

* academic bench ifeval&math update

* generic_llmjudge_aime_academic_postprocess delete

* aime delete

* postprocessors update

* ifeval delete

* update work_dir

* linting

* linting double-quote-string-fixer

* r1-distill out_len update

* fix lint

---------

Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>
2025-02-24 15:45:24 +08:00
..
aime2024_0shot_nocot_gen_2b9dc2.py [Update] Update Fullbench (#1712) 2024-11-26 14:26:55 +08:00
aime2024_0shot_nocot_genericllmeval_academic_gen.py [Update] Academic bench llm judge update (#1876) 2025-02-24 15:45:24 +08:00
aime2024_0shot_nocot_genericllmeval_gen_2b9dc2.py [Feature] Update o1 evaluation with JudgeLLM (#1795) 2024-12-30 17:31:00 +08:00
aime2024_0shot_nocot_genericllmeval_xml_gen_2b9dc2.py [Refactor] Code refactoarization (#1831) 2025-01-20 19:17:38 +08:00
aime2024_0shot_nocot_llmjudge_gen_2b9dc2.py [Update] Update Skywork/Qwen-QwQ (#1728) 2024-12-05 19:30:43 +08:00
aime2024_gen_6e39a4.py [Datasets] Add datasets CMO&AIME (#1610) 2024-10-28 18:08:02 +08:00
aime2024_gen.py [Datasets] Add datasets CMO&AIME (#1610) 2024-10-28 18:08:02 +08:00
README.md [Datasets] Add datasets CMO&AIME (#1610) 2024-10-28 18:08:02 +08:00

Description

Math dataset composed of problems from AIME2024 (American Invitational Mathematics Examination 2024).

Performance

Qwen2.5-Math-72B-Instruct Qwen2.5-Math-7B-Instruct Qwen2-Math-7B-Instruct Qwen2-Math-1.5B-Instruct internlm2-math-7b
20.00 16.67 16.67 13.33 3.33
Qwen2.5-72B-Instruct Qwen2.5-7B-Instruct internlm2_5-7b-chat
31.25 26.44 9.13