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 | 32k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.256DeepInfra | $0.04DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.712DeepInfra | $0.064DeepInfra |
| $103StreamLake | $14.00DeepInfra · fp8 | |
| 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. | 42% | — |
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. | 40.5% | — |
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. | — | 84.8% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 82.9% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 70.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 59.1% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 66.3% |
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. | 88.5% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Dec 26 2024 | Jan 30 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3vsClaude Fable 5.2Mistral Small 3vsClaude Fable 5.2DeepSeek V3vsGPT-6.2 AstraMistral Small 3vsGPT-6.2 AstraDeepSeek V3vsGemini 4 HydrogenMistral Small 3vsGemini 4 HydrogenDeepSeek V3vsMuse EmberMistral Small 3vsMuse EmberDeepSeek V3vsGrok 4.7Mistral Small 3vsGrok 4.7DeepSeek V3vsKimi K3.1 ProMistral Small 3vsKimi K3.1 ProFrequently asked questions
DeepSeek V3 and Mistral Small 3 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V3 shipped 35 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.
DeepSeek V3 has 671B parameters, while Mistral Small 3 has 24B. Context windows are 128k (DeepSeek V3) vs 32k (Mistral Small 3).
Direct benchmark comparisons are unavailable — DeepSeek V3 and Mistral Small 3 don't publish scores on any of the same benchmarks.