STEM
multimodal
+
+
+
+
About
STEM is a comprehensive benchmark evaluating AI models' capabilities across Science, Technology, Engineering, and Mathematics domains, testing knowledge integration and problem-solving skills in technical fields. This multidisciplinary evaluation assesses models' ability to apply scientific principles, mathematical reasoning, engineering concepts, and technological understanding in diverse STEM contexts and applications.
+
+
+
+
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
34.0%
Average Score
34.0%
High Performers (80%+)
0Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
34.0%
+
+
+
+
Leaderboard
1 models ranked by performance on STEM
| License | Links | ||||
|---|---|---|---|---|---|
| Sep 19, 2024 | Apache 2.0 | 34.0% |
