Math
AIME 2025 leaderboard
As of 2026-10-07, the highest measured score on AIME 2025 is 99.0% by GPT-5.2 (xhigh).
Measured scores: artificial-analysis.
| # | Model | Score | Source |
|---|---|---|---|
| 1 | GPT-5.2 (xhigh) | 99.0% | measured |
| 2 | GPT-5 Codex (high) | 98.7% | measured |
| 3 | Gemini 3 Flash | 97.0% | measured |
| 4 | GPT-5.2 (medium) | 96.7% | measured |
| 5 | DeepSeek V3.2 Speciale | 96.7% | measured |
All leaderboards
Agentic · terminal
Agentic · tools
- AA-AnalystAgent
- APEX-Agents
- AutomationBench
- EnterpriseOps-Gym
- Harvey LAB
- ITBench SRE
- τ³-Bench Banking
- τ²-Bench Telecom