2 vs 1 benchmarks won
Google Gemini 3.0 Pro | OpenAI GPT-5.4 | |
|---|---|---|
| Overview | ||
| Company | OpenAI | |
| Release date | Nov 18 2025 | Mar 5 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.9% | 92.8% |
Software engineering SWE-Bench Verified | 76.2% | — |
Multimodal understanding MMMU | 81% | — |
| Timeline | ||
| Release gap | Gemini 3.0 Pro shipped 107 days before GPT-5.4 | |
Gemini 3.0 Pro leads GPT-5.4 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Gemini 3.0 Pro shipped 107 days before GPT-5.4, 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, GPT-5.4 scores 92.8%, 0.9 points above Gemini 3.0 Pro at 91.9%.