Compare Models
Select 2–4 models to compare side-by-side across all benchmarks.
3/4 models selected — click to add or remove
Capability Profile
Average score across benchmarks in each category. Higher = better.
Pricing (per million tokens)
GPT-5
Input$3.00
Output$15.00
Opus 4.6
Input$15.00
Output$75.00
Gemini 2.5 Pro
Input$1.25
Output$10.00
| Benchmark | GPT-5 | Opus 4.6 | Gemini 2.5 Pro |
|---|---|---|---|
| 74.9% | 80.8% | 67.2% (multi) | |
| 96.9% | — | 94.2% | |
| 66.3% | — | — | |
| ~79% | — | — | |
| ~95%+ | ~97–98% | — | |
| 99.7% | — | ~98% | |
| 85.7% | 91.3% | 86.4% | |
| 93.0% | ~90.8% | 89.2% | |
| 94.6% | 99.79% | 88.0% | |
| ~91% | — | 89.2% | |
| ~75% | — | — | |
| ~97% | — | — | |
| 96.4% | — | — | |
| 67.0% | — | ~52% | |
| 58.1% | — | ~48% | |
| 6.8 | — | — | |
| ~79% | — | ~48% | |
| ~24% | — | 30.3% | |
| ~1426 Elo | 1549 Elo (Coding) | 1448 Elo | |
| ~82% | — | ~76% | |
| — | — | — | |
| — | — | — | |
HLENEW | — | — | — |
ARC-AGI-2NEW | — | — | — |
FrontierMathNEW | — | — | — |
OSWorldNEW | — | — | — |
BigCodeBenchNEW | — | — | — |
Video-MMENEW | — | — | — |
MMMU-ProNEW | — | — | — |