MathArena
We track 19 benchmarks that MathArena made or helped make.
5 in use 19 with public code 13 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| AIME 2026 Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. | Competition problems with answers | Feb 2026 | 100% | In use |
| HMMT Nov 2025 Models solve the 30 problems of the November 2025 Harvard-MIT Mathematics Tournament. Final answers are checked automatically against the answer key. | Competition problems with answers | Nov 2025 | 99.2% | Fading |
| HMMT 2026 Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. | Competition problems with answers | Feb 2026 | 98.5% | In use |
| ArXivMath Final-answer research-level math problems extracted monthly from recent arXiv papers and filtered to be self-contained. | Research mathematics | Feb 2026 |  94.3% | In use |
| USAMO 2026 Models write full proofs for the six problems of the 2026 USA Mathematical Olympiad. Judges grade each proof from 0 to 7 against rubrics. | Written proofs | Mar 2026 | 98.2% | In use |
| Math Kangaroo 2025 (MathArena) Vision language models answer 168 multiple-choice problems from the 2025 Math Kangaroo, given as screenshots across six grade groups. Many problems need reading a diagram. | Visual math and diagrams | Oct 2025 | 94.9% | Fading |
| USAMO 2025 Models write full proofs for the 6 problems of the 2025 USA Mathematical Olympiad. Expert human graders score each proof. | Written proofs | Mar 2025 |  30.1% | Dropped |
| ArXivLean Models prove or disprove theorems from recent arXiv papers, stated in Lean 4. A strict comparator checks each submitted proof against the fixed reference statement. | Formal proofs | Apr 2026 | 62.3% | System cards only |
| BrokenArXiv Models are asked to prove statements from recent arXiv papers that were changed to be plausible but false. Full credit goes to models that say the statement is false. | Research mathematics | Mar 2026 | 84.4% | In use |
| BRUMO 2025 Models answer the 30 final-answer problems of the 2025 Brown University Math Olympiad. MathArena scores the average accuracy over four attempts. | Competition problems with answers | Apr 2025 | 100% | Not in cards |
| SMT 2025 Models answer 53 final-answer problems from the 2025 Stanford Math Tournament. MathArena scores the average accuracy over four attempts. | Competition problems with answers | May 2025 | 93.4% | Not in cards |
| CMIMC 2025 Models answer 40 final-answer problems from the 2025 Carnegie Mellon Informatics and Mathematics Competition. MathArena scores the average accuracy over four attempts. | Competition problems with answers | May 2025 | 95.6% | Not in cards |
| Project Euler (MathArena) Models solve recent Project Euler problems that need both mathematical insight and code. MathArena adds problems as Project Euler releases them, starting from problem 943. | Competition problems with answers | Sep 2025 | 89% | Not in cards |
| IMC 2025 Models write proofs for the 10 problems of the 2025 International Mathematics Competition for University Students. Human judges grade each proof. | Written proofs | Aug 2025 | 94.5% | Not in cards |
| Miklós Schweitzer 2025 Models write proofs for the 2025 Miklós Schweitzer competition, a hard Hungarian university-level contest. MathArena runs and grades it. | Written proofs | Dec 2025 | 90% | Not in cards |
| ArXivCS Models answer research-level computer science questions derived from recent arXiv papers, each with a reference final answer. The first set has 46 questions from August 2026. | Scientific code | Sep 2026 | Not in cards | |
| ArXivPhys Models answer research-level physics questions derived from recent arXiv papers, each with a reference final answer. | Research science | Sep 2026 | Not in cards | |
| ProofRank Models write proofs for hard competition problems. An LLM judge compares correct proofs pairwise on conciseness, computational ease, simplicity, diversity and adaptivity, giving Elo ratings. | Written proofs | May 2026 | Not in cards | |
| USAMO 2024 Models write full proofs for problems from the 2024 USA Mathematical Olympiad, graded by human experts. | Written proofs | Mar 2024 | Not in cards |