Quality
#17/6740.3
Overall quality score
🇨🇳DeepSeekOpen sourceDeepSeek: DeepSeek V4 Flash.
See how DeepSeek: DeepSeek V4 Flash compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#23/6792 t/s
Output tokens per second
Input price
#20/67$0.14/1M
Per 1M tokens
Output price
#13/67$0.28/1M
Per 1M tokens
Context
#16/671M
Content read at once
Comparison summary
DeepSeek: DeepSeek V4 Flash ranks #17 of 67 for overall quality and #23 for response speed in the current catalogue.
Its listed input price is $0.14/1M, output price is $0.28/1M, and it can work with up to 1M of context at once.
Its strongest areas in the current data are coding, everyday help, math and logic.
Practical specifications
- Company
- DeepSeek
- Reasoning
- Yes
- Open weights
- Yes
- Input
- Text
- Output
- Text
- Context window
- 1M
DeepSeek: DeepSeek V4 Flash technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | DeepSeek V4 Flash | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 40.3 | OpenRouter / artificial-analysis |
| Coding Index | coding | 56.2 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 31.1 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 89.4 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 32.1 | OpenRouter model benchmarks |
| IFBench | IFBench | 79.2 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 95 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 63 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 34.3 | OpenRouter model benchmarks |
| CritPt | CritPt | 7.1 | OpenRouter model benchmarks |
| SciCode | SciCode | 44.9 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 35.6 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 37.2 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 4.2 | OpenRouter model benchmarks |
Quality benchmarks
See where DeepSeek: DeepSeek V4 Flash stands.
The darker bar marks DeepSeek: DeepSeek V4 Flash; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better