ArXivLean 03/2026
Math · 2026-04-21
This MathArena track evaluates models on the ArXivLean 03/2026 problem set. Scores report the percentage of problems answered correctly.
Top models (higher is better)
| Model | Score |
|---|---|
| Aristotle | 17.1 |
| GPT-5.4 | 17.1 |
| GPT-5.5 | 17.1 |
| Opus 4.7 | 14.6 |
| Gemini 3.1 Pro Preview | 14.6 |
| GLM-5.1 | 2.4 |
| Step 3.5 Flash | 0.0 |