Compare, 2 models
Side by side.
DeepSeek V4.1 Flash 1017 and Gemini 3.7 Flash on every board at least two of them share. Blue marks the best in each row.
Specs
List prices, context and published output speed. Blue marks the best in each row.
| Spec | DeepSeek V4.1 Flash 1017DeepSeek | Gemini 3.7 FlashGoogle |
|---|---|---|
| Lab | DeepSeek | |
| Type | Language | Language |
| Released | Oct 17, 2026 | Aug 13, 2026 |
| Input price$ per 1M tokens | $0.30 | $0.75 |
| Output price$ per 1M tokens | $1.20 | $3.75 |
| Blended price3 input tokens per output | $0.52 | $1.50 |
| Contexttokens | 1.05M | 1.05M |
| Open weights | Yes | No |
| Output speedTok / s | 164 | n/a |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | DeepSeek V4.1 Flash 1017DeepSeek | Gemini 3.7 FlashGoogle |
|---|---|---|
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 71.2%max setting | 71.6%high setting |
| GPQA DiamondReasoning and knowledge, higher is better | 93.2%max setting | 94.8%high setting |
n/a means the board has not published a score for that model.