ArXivMath
Progress Over Time
Interactive timeline showing model performance evolution on ArXivMath
ArXivMath Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Anthropic | — | 1.0M | $4.00 / $20.00 | ||
| 2 | Anthropic | — | 1.0M | $2.00 / $10.00 | ||
| 3 | Anthropic | — | 1.0M | $2.00 / $10.00 | ||
| 4 |  Tencent | 770B | — | — | ||
| 5 | Tencent | 295B | 262K | $0.14 / $0.58 |
Sub-benchmarks
What is ArXivMath?
ArXivMath is a final-answer benchmark of research-level mathematics maintained by MathArena. Problems are extracted monthly from recent arXiv paper abstracts, then filtered through automated and manual checks to ensure they are self-contained, non-trivial, and verifiable. Because problems are drawn from active research, the benchmark is more realistic and more closely connected to mathematical research than contest or olympiad benchmarks.
ArXivMath is a text benchmark evaluating models on math and reasoning tasks. LLM Stats tracks 5 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.9.
Compare leaders on the best AI for math and best AI for reasoning leaderboards.
Current leaders
Claude Opus 5.5 from Anthropic currently leads the ArXivMath leaderboard with a score of 0.912 across 5 evaluated AI models.
FAQ
Common questions about the ArXivMath benchmark and leaderboard.