Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 236B | — |
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 | 128k |
| Benchmarks | ||
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. | 16.8% | 61.6% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 41.8% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 89% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Sep 5 2024 | Jul 10 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Fable 5.2Devstral MediumvsClaude Fable 5.2DeepSeek V2.5vsGPT-6.2 AstraDevstral MediumvsGPT-6.2 AstraDeepSeek V2.5vsGemini 4 HydrogenDevstral MediumvsGemini 4 HydrogenDeepSeek V2.5vsMuse EmberDevstral MediumvsMuse EmberDeepSeek V2.5vsGrok 4.7Devstral MediumvsGrok 4.7DeepSeek V2.5vsKimi K3.1 ProDevstral MediumvsKimi K3.1 ProFrequently asked questions
Devstral Medium leads DeepSeek V2.5 on 1 of the 1 benchmark they both report (SWE-Bench Verified). DeepSeek V2.5 shipped 308 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V2.5) vs 128k (Devstral Medium). DeepSeek V2.5 is open weight, while Devstral Medium is closed.
On SWE-Bench Verified, Devstral Medium leads at 61.6% vs DeepSeek V2.5 at 16.8%.