ArXivLean 03/2026 (MathArena IRT estimate)
Math
Estimated accuracy on the March 2026 ArXivLean set includes item-response-theory predictions for unanswered questions. Diagnostic only, separate from verified problem success and excluded from the capability fit.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 20.1 |