0 vs 3 benchmarks won
Anthropic Claude Haiku 4.5 | Google Gemini 3.0 Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | |
| Release date | Oct 15 2025 | Nov 18 2025 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 73% | 91.9% |
Software engineering SWE-Bench Verified | 73.3% | 76.2% |
Multimodal understanding MMMU | — | 81% |
| Timeline | ||
| Release gap | Claude Haiku 4.5 shipped 34 days before Gemini 3.0 Pro | |
Gemini 3.0 Pro leads Claude Haiku 4.5 on 3 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Haiku 4.5 shipped 34 days before Gemini 3.0 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 3.0 Pro scores 91.9%, 18.9 points above Claude Haiku 4.5 at 73%. On SWE-Bench Verified, Gemini 3.0 Pro scores 76.2%, 2.9 points above Claude Haiku 4.5 at 73.3%.