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. | 671B | 24B |
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 | 256k |
| 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. | 49.2% | 68% |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 55.7% |
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. | 65.9% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 22.5% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.3% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 92.2 | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 79.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 71.5% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 30.1% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 84% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 90.8% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Jan 20 2025 | Dec 9 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1vsClaude Fable 5.2Devstral Small 2 (24B)vsClaude Fable 5.2DeepSeek R1vsGPT-6.2 AstraDevstral Small 2 (24B)vsGPT-6.2 AstraDeepSeek R1vsGemini 4 HydrogenDevstral Small 2 (24B)vsGemini 4 HydrogenDeepSeek R1vsMuse EmberDevstral Small 2 (24B)vsMuse EmberDeepSeek R1vsGrok 4.7Devstral Small 2 (24B)vsGrok 4.7DeepSeek R1vsKimi K3.1 ProDevstral Small 2 (24B)vsKimi K3.1 ProFrequently asked questions
Devstral Small 2 (24B) leads DeepSeek R1 on 1 of the 1 benchmark they both report (SWE-Bench Verified). DeepSeek R1 shipped 323 days before Devstral Small 2 (24B), so benchmark comparisons should account for the intervening progress.
DeepSeek R1 has 671B parameters, while Devstral Small 2 (24B) has 24B. Context windows are 128k (DeepSeek R1) vs 256k (Devstral Small 2 (24B)).
On SWE-Bench Verified, Devstral Small 2 (24B) leads at 68% vs DeepSeek R1 at 49.2%.