International Mathematical Olympiad 2025 (reported)
Math
Provider-reported normalized partial-credit score on the six 2025 IMO problems. The evaluation's prompting, grading and repeated-generation settings remain in the score provenance; this is a component alongside the independently run MathArena cohort.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3 Deep Think | 81.5 |