Compare
Devstral Small 2 vs Grok 4.6
Devstral Small 2 (Mistral AI) and Grok 4.6 (xAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Grok 4.6 ranks higher for coding (92th vs 5th percentile).
| Attribute | Devstral Small 2 | Grok 4.6 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 156 |
| Coding | 5 | 92 |
| Math | 1 | 92 |
| Reasoning & Knowledge | 1 | 73 |
| Agentic & Tools | 2 | 85 |
| Specifications | ||
| Developer | Mistral AI | xAI |
| Family | — | Grok |
| Released | Dec 9, 2025 | Aug 12, 2026 |
| Parameters | — | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | — | 500K |
| Price — $/M input | — | $2.00 |
| Price — $/M output | — | $6.00 |
| Inputs | — | text, image, file |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 34% | 99% |
| GPQA Diamond | 53% | 94% |
| Humanity's Last Exam | 4% | 43% |
| LiveCodeBench | 35% | — |
| MMLU-Pro | 68% | — |
| SciCode | 32% | 56% |
| τ²-bench | 23% | — |
| APEX | — | 41% |
| ARC-AGI | — | 88% |
| ARC-AGI-2 | — | 67% |
| SimpleBench | — | 76% |
| SimpleQA Verified | — | 49% |
| WebDev Arena | — | 1629 |
| WeirdML | — | 67% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is better for coding, Devstral Small 2 or Grok 4.6?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.6 ranks higher — 92th vs 5th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.