Gemini 2.5 Pro (Mar' 25) — benchmark results
Provider: Google. Released 2025-03-25. Access: API.
Unified ELO 1792 ± 43, rank #153 of 1841 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA MMLU-Pro | 85.75 | Accuracy (%) | 93 |
| AA MATH-500 | 98 | Accuracy (%) | 91.3 |
| AA LiveCodeBench | 77.78 | Pass@1 (%) | 89.8 |
| AA GPQA Diamond | 83.64 | Accuracy (%) | 79 |
| AA Humanity's Last Exam | 17.13 | Accuracy (%) | 75.3 |
| Epoch AI - Scicode | 39.47 | Score | 68.7 |
| Artificial Analysis Intelligence Index | 23.03 | Intelligence Index | 65 |
Interactive version: theaggregate.ai/model?slug=gemini-2-5-pro-mar-25 · How It Works · Data refreshed daily, snapshot 2026-07-25.