Compare AI models
| Specifications | ||
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 200k |
| These models have no shared benchmark scores. | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 61.6% | — |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Jul 10 2025 | May 16 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Devstral MediumvsClaude Fable 5.2codex-mini-latestvsClaude Fable 5.2Devstral MediumvsGemini 4 Hydrogencodex-mini-latestvsGemini 4 HydrogenDevstral MediumvsMuse Embercodex-mini-latestvsMuse EmberDevstral MediumvsGrok 4.7codex-mini-latestvsGrok 4.7Devstral MediumvsDeepSeek-V4.1-Flash-1017codex-mini-latestvsDeepSeek-V4.1-Flash-1017Devstral MediumvsKimi K3.1 Procodex-mini-latestvsKimi K3.1 ProFrequently asked questions
Devstral Medium and codex-mini-latest don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. codex-mini-latest shipped 55 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Devstral Medium) vs 200k (codex-mini-latest).
Direct benchmark comparisons are unavailable — Devstral Medium and codex-mini-latest don't publish scores on any of the same benchmarks.