Quality
Highest overall scores
- 1
DeepSeek: DeepSeek V4 Flash 073151.8 - 2DeepSeek: DeepSeek V4 Pro 081345.3
- 3DeepSeek: DeepSeek V4 Flash 04230
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 Flash 0731153 t/s
- 2DeepSeek: DeepSeek V4 Flash 042381 t/s
- 3DeepSeek: DeepSeek V4 Pro 081348 t/s
Input price
Lowest price per 1M tokens
- 1DeepSeek: DeepSeek V4 Flash 0731$0.08/1M
- 2DeepSeek: DeepSeek V4 Flash 0423$0.14/1M
- 3DeepSeek: DeepSeek V4 Pro 0813$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 | 51.8 | 153 t/s | 1M | $0.08 | $0.18 | |
| DeepSeek: DeepSeek V4 Pro 0813 | 45.3 | 48 t/s | 1M | $0.43 | $0.87 | |
| DeepSeek: DeepSeek V4 Flash 0423 | 0 | 81 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 0813 | DeepSeek V4 Flash 0423 | Source |
|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 51.8 | 45.3 | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 69.1 | 59.4 | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 48.4 | 37.8 | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 90.8 | 88.8 | 71.6 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 38.6 | 37.5 | 7.8 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 74.3 | 70 | 37.3 | 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 | 40.4 | 42.9 | 26 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 8.3 | 5.9 | 5.5 | 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 |