Gemini 3.7 Flash vs GPT-5.4 Pro
Gemini 3.7 Flash 
GPT-5.4 Pro Verdict
- Gemini 3.7 Flash (medium) and GPT-5.4 Pro are level on quality (64.4 vs 64.2).
- Gemini 3.7 Flash (medium) is stronger in coding, composite, knowledge, long context.
- GPT-5.4 Pro is stronger in multimodal, reasoning, instruction following.
- Gemini 3.7 Flash (medium) is 45× cheaper ($1.50 vs $67.50 per 1M blended).
- Gemini 3.7 Flash (medium) streams 282.4× faster (282 vs 1 tokens per second).
| Metric | Gemini 3.7 Flash (medium) | GPT-5.4 Pro |
|---|---|---|
| BenchLeader Index | 64.4 | 64.2 |
| Coding score | 68.3 | – |
| Composite score | 78.9 | – |
| Knowledge score | 75.2 | 73.2 |
| Long context score | 68.1 | – |
| Multimodal score | 69.4 | 69.8 |
| Reasoning score | 63.5 | 75.1 |
| Instruction following score | – | 67.3 |
| Blended price $/M | $1.50 | $67.50 |
| Output speed | 282 tok/s | 1 tok/s |
| Time to first answer | 5.3 s | 6.7 s |
| Context window | 1M | 1.1M |
| Humanity's Last Exam | – | 44.3% |
| SimpleBench | – | 74.1% |
| SciCode | 57.9% | – |
| Epoch Capabilities Index | – | 158.9 |
| AA Intelligence Index | 39.6 | – |
| AA-LCR | 83.0% | – |
| MMMU-Pro | 84.7% | – |
| AA-Omniscience | 23.7 | – |
| GPQA Diamond (AA) | 92.1% | – |
| Humanity's Last Exam (AA) | 39.0% | – |
| SciCode (AA) | 59.8% | – |
| MultiChallenge | – | 69.2% |
| VISTA | – | 53.9% |
| MultiNRC | – | 62.3% |
| TutorBench | – | 56.6% |
| ARC-AGI-1 | 91.2% | – |
| ARC-AGI-2 | 63.8% | – |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.