OlympiadBench
Multilingual
multimodal
+
+
+
+
About
OlympiadBench is an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from mathematics and physics competitions, including Chinese college entrance exams. It challenges models with competition-grade scientific problems requiring advanced mathematical reasoning, physics understanding, and multimodal problem-solving capabilities at the highest academic levels.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
20.4%
Average Score
20.4%
High Performers (80%+)
0Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
20.4%
+
+
+
+
Leaderboard
1 models ranked by performance on OlympiadBench
| License | Links | ||||
|---|---|---|---|---|---|
| Dec 25, 2024 | Qwen | 20.4% |
