Compare
Devstral Small 2 vs GPT-5.6 Sol
Devstral Small 2 (Mistral AI) and GPT-5.6 Sol (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
- GPT-5.6 Sol ranks higher for coding (95th vs 3th percentile).
| Attribute | Devstral Small 2 | GPT-5.6 Sol |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 162 |
| Coding | 3 | 95 |
| Math | 0 | 97 |
| Reasoning & Knowledge | 0 | 95 |
| Agentic & Tools | 2 | 67 |
| Specifications | ||
| Developer | Mistral AI | OpenAI |
| Family | — | GPT |
| Released | Dec 9, 2025 | Jul 9, 2026 |
| Parameters | — | — |
| Availability | — | API access |
| Context window | — | 1.1M |
| Price — $/M input | — | $5.00 |
| Price — $/M output | — | $30.00 |
| Inputs | — | file, image, text |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 34% | 100% |
| GPQA Diamond | 53% | 93% |
| Humanity's Last Exam | 3% | 47% |
| LiveCodeBench | 35% | — |
| MMLU-Pro | 68% | — |
| SciCode | 29% | 56% |
| τ²-bench | 23% | 85% |
| APEX | — | 40% |
| ARC-AGI | — | 98% |
| ARC-AGI-2 | — | 93% |
| SimpleBench | — | 72% |
| SimpleQA Verified | — | 72% |
| WeirdML | — | 89% |
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 GPT-5.6 Sol?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, GPT-5.6 Sol ranks higher — 95th vs 3th 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.