What it measures
Bilingual, multimodal olympiad-level mathematics benchmark spanning IMO, regional olympiads, and Gaokao hard problems.
Reading the measurement
Partial credit can distinguish a useful approach from an empty attempt, but it is not the same as a completed task. Read the rubric, full-success count and score distribution together. For mathematical work, preserve the difference between expert review and acceptance by a formal proof checker.
Published evaluation
Mathematics · Full multimodal benchmark; Full multimodal benchmark. The table retains the source’s reported model and evaluation configuration.
Where this fits in an evaluation suite
Final-answer accuracy, proof credit, and expert-reviewed research progress are distinct signals. A proof-aware evaluation should retain partial work and audit strong claims.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Mathematics · Full multimodal benchmark; Full multimodal benchmark. The table retains the source’s reported model and evaluation configuration.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems — published result table ↗
All 14 authors
Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.