Deepseek v4 Pro vs Gemini 3.7 Flash
Deepseek v4 Pro 
Gemini 3.7 Flash Verdict
- Gemini 3.7 Flash (medium) leads on quality: 63.0 vs 60.4.
- Deepseek v4 Pro (high) is stronger in human preference, maths, reasoning.
- Gemini 3.7 Flash (medium) is stronger in coding, composite, knowledge, long context, multimodal.
| Metric | Deepseek v4 Pro (high) | Gemini 3.7 Flash (medium) |
|---|---|---|
| BenchLeader Index | 60.4 | 63.0 |
| Coding score | 59.3 | 68.5 |
| Human preference score | 66.0 | – |
| Maths score | 66.2 | – |
| Reasoning score | 65.9 | 63.5 |
| Composite score | – | 72.3 |
| Knowledge score | – | 72.0 |
| Long context score | – | 65.8 |
| Multimodal score | – | 68.9 |
| Blended price $/M | – | $1.50 |
| Output speed | – | 311 tok/s |
| Time to first answer | – | 4.3 s |
| Context window | – | 1.0M |
| GPQA Diamond | 90.9% | – |
| OTIS Mock AIME | 95.6% | – |
| SciCode | 46.4% | 57.9% |
| WeirdML | 46.5% | – |
| LMArena Text | 1462 | – |
| LMArena Hard Prompts | 1482 | – |
| LMArena Coding | 1505 | – |
| LMArena WebDev | 1581 | – |
| 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% |
| ARC-AGI-1 | – | 91.2% |
| ARC-AGI-2 | – | 63.8% |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Deepseek v4 Pro vs Gemini 3.7 Flash: questions
- Is Deepseek v4 Pro better than Gemini 3.7 Flash?
- Gemini 3.7 Flash (medium) leads on quality: 63.0 vs 60.4. The BenchLeader Index combines every independent quality benchmark; Gemini 3.7 Flash (medium) is ahead overall as of 2026-09-13, but check the category scores for your use.
- Is Deepseek v4 Pro better than Gemini 3.7 Flash for coding?
- Gemini 3.7 Flash scores higher in coding (69 vs 59 on the category index, where 50 is average).