0 vs 3 benchmarks won
Anthropic Claude 3.5 Sonnet | Google Gemini 2.5 Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | |
| Release date | Jun 20 2024 | Mar 25 2025 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 59.4% | 86.4% |
Software engineering SWE-Bench Verified | 33.4% | 59.6% |
Multimodal understanding MMMU | — | 68% |
| Timeline | ||
| Release gap | Claude 3.5 Sonnet shipped 278 days before Gemini 2.5 Pro | |
Gemini 2.5 Pro leads Claude 3.5 Sonnet on 3 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude 3.5 Sonnet shipped 278 days before Gemini 2.5 Pro, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, Gemini 2.5 Pro scores 86.4%, 27 points above Claude 3.5 Sonnet at 59.4%. On SWE-Bench Verified, Gemini 2.5 Pro scores 59.6%, 26.2 points above Claude 3.5 Sonnet at 33.4%.