Quality
#29/6719.6
Overall quality score
🇫🇷Mistral AIOpen sourceMistral: Mistral Small 4.
See how Mistral: Mistral Small 4 compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#24/6789 t/s
Output tokens per second
Input price
#23/67$0.15/1M
Per 1M tokens
Output price
#24/67$0.60/1M
Per 1M tokens
Context
#36/67262.1K
Content read at once
Comparison summary
Mistral: Mistral Small 4 ranks #29 of 67 for overall quality and #24 for response speed in the current catalogue.
Its listed input price is $0.15/1M, output price is $0.60/1M, and it can work with up to 262.1K of context at once.
Its strongest areas in the current data are coding, everyday help, math and logic.
Practical specifications
- Company
- Mistral AI
- Reasoning
- Yes
- Open weights
- Yes
- Input
- Text, Image
- Output
- Text
- Context window
- 262.1K
Mistral: Mistral Small 4 technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Mistral Small 4 | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 19.6 | OpenRouter / artificial-analysis |
| Coding Index | coding | 26.6 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 4.7 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 76.9 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 9.5 | OpenRouter model benchmarks |
| IFBench | IFBench | 48.2 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 41.2 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 44.7 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 4.6 | OpenRouter model benchmarks |
| CritPt | CritPt | 0.3 | OpenRouter model benchmarks |
| SciCode | SciCode | 38 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 17.4 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 22.1 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 33.2 | OpenRouter model benchmarks |
Quality benchmarks
See where Mistral: Mistral Small 4 stands.
The darker bar marks Mistral: Mistral Small 4; 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