AMC_2022_23
text
+
+
+
+
About
AMC 2022-23 is an AI benchmark derived from American Mathematics Competitions problems from 2022 and 2023, designed to evaluate large language models' mathematical reasoning capabilities. This challenging dataset tests AI systems on competition-level mathematics problems requiring advanced problem-solving techniques, logical reasoning, and mathematical knowledge across algebra, geometry, number theory, and combinatorics. Used extensively in LLM evaluation.
+
+
+
+
Evaluation Stats
Total Models2
Organizations1
Verified Results0
Self-Reported2
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
2 models
Top Score
46.4%
Average Score
40.6%
High Performers (80%+)
0Top Organizations
#1Google
2 models
40.6%
+
+
+
+
Leaderboard
2 models ranked by performance on AMC_2022_23
| License | Links | ||||
|---|---|---|---|---|---|
| May 1, 2024 | Proprietary | 46.4% | |||
| May 1, 2024 | Proprietary | 34.8% |
