Quality
Highest overall scores
- 1
DeepSeek: DeepSeek V4 Flash 073149.9 - 2DeepSeek: DeepSeek V4 Pro44.3
- 3DeepSeek: DeepSeek V4 Flash0
DeepSeek model benchmarks.
Compare DeepSeek models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1DeepSeek: DeepSeek V4 Flash92 t/s
- 2DeepSeek: DeepSeek V4 Pro87 t/s
- 3DeepSeek: DeepSeek V4 Flash 07310 t/s
Input price
Lowest price per 1M tokens
- 1DeepSeek: DeepSeek V4 Flash 0731$0.14/1M
- 2DeepSeek: DeepSeek V4 Flash$0.14/1M
- 3DeepSeek: DeepSeek V4 Pro$0.43/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare DeepSeek model capability.
Performance and price
Compare practical tradeoffs.
All DeepSeek models.
3 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4 Flash 0731 | 49.9 | — | 1M | $0.14 | $0.28 | |
| DeepSeek: DeepSeek V4 Pro | 44.3 | 87 t/s | 1M | $0.43 | $0.87 | |
| DeepSeek: DeepSeek V4 Flash | 0 | 92 t/s | 1M | $0.14 | $0.28 |
DeepSeek technical benchmarks.
Compare named evaluation records available for DeepSeek models. Missing results remain blank rather than being estimated.
| Benchmark | Area | DeepSeek V4 Flash 0731 | DeepSeek V4 Pro | DeepSeek V4 Flash | Source |
|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 49.9 | 44.3 | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 69.1 | 59.4 | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 45.7 | 36.4 | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 90.8 | 88.8 | 71.6 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 36.8 | 35.9 | 7 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 65.7 | 66.3 | 33.3 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 52.9 | 40.3 | — | OpenRouter model benchmarks |
| CritPt | CritPt | 16.6 | 12.9 | 0.3 | OpenRouter model benchmarks |
| SciCode | SciCode | 49.9 | 50 | 37.3 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 37.2 | 43.3 | 26.1 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 15.6 | 6 | 4.9 | OpenRouter model benchmarks |
| IFBench | IFBench | — | 76.5 | 47.2 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | — | 96.2 | 94.4 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | — | 46.2 | 34.1 | OpenRouter model benchmarks |