Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
devstral-small-2505
deepinfra
Context128K tokens
Input Price$0.06 / 1M tokens
Output Price$0.12 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.06 / 1M tokens | $3 / 1M tokens |
| Output Price | $0.12 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 128K tokens | 256K tokens |
| Capabilities | tools | |
| Input type | text | text |
Category Scores | ||
| Overall Average | 27.8 | 71.3 |
| Academia | 31.5 | 76.4 |
| Finance | 28.6 | 81.0 |
| Marketing | 14.4 | 51.5 |
| Maths | 37.5 | 96.7 |
| Programming | 25.2 | 63.8 |
| Science | 43.4 | 87.6 |
| Writing | 14.0 | 42.2 |
Benchmark Tests | ||
| AIME | 6.7 | 94.3 |
| AA Coding Index | 25.2 | 63.8 |
| AAII | 19.6 | 65.3 |
| AA Math Index | 37.5 | 96.7 |
| GPQA | 43.4 | 87.6 |
| HLE | 4.0 | 23.9 |
| LiveCodeBench | 25.8 | 81.9 |
| MATH-500 | 68.4 | 99.0 |
| MMLU-Pro | 63.2 | 86.6 |
| SciCode | 24.5 | 45.7 |
devstral-small-2505 Advantages
- • Lower input token cost ($0.06 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (71.3 vs 27.8)
- • Larger context window (256K tokens vs 128K tokens)