Physics Olympiad Reasoning on IPhO 2024
25.9PointsGemini 3.1 Pro Thinking
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3.1 Pro ThinkingModel Category=Larger models2026.05 | 25.9 | |
| GPT-5.5-HighModel Category=Larger models2026.05 | 25.8 | |
| SU-01Model Category=Similar-size models, test-time scaling=true2026.05 | 25.3 | |
| DeepSeek-V3.2-SpecialeModel Category=Larger models2026.05 | 25.1 | |
| Gemma-4-31BModel Category=Similar-size models2026.05 | 24.4 | |
| Qwen3.6-35B-A3BModel Category=Similar-size models2026.05 | 24.3 | |
| SU-01Model Category=Similar-size models, test-time scaling=false2026.05 | 23.5 | |
| P1-30B-A3BModel Category=Similar-size models2026.05 | 23.1 | |
| GLM-4.7-FlashModel Category=Similar-size models2026.05 | 22.2 | |
| Nemotron-Cascade-2Model Category=Similar-size models2026.05 | 21.2 |