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 | — |
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 |
| 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. | $0.27SiliconFlow | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | — |
| $104SiliconFlow · fp8 | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.7% | 65.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 85% | 76.8% |
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. | 68.4% | — |
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. | 57.8% | — |
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. | 74.9% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 38.5% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 88.4% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 40.8% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 43.8% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Sep 22 2025 | Aug 12 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1 TerminusvsClaude Fable 5.2Mistral Medium 3.1vsClaude Fable 5.2DeepSeek V3.1 TerminusvsGPT-6.2 AstraMistral Medium 3.1vsGPT-6.2 AstraDeepSeek V3.1 TerminusvsGemini 4 HydrogenMistral Medium 3.1vsGemini 4 HydrogenDeepSeek V3.1 TerminusvsMuse EmberMistral Medium 3.1vsMuse EmberDeepSeek V3.1 TerminusvsGrok 4.7Mistral Medium 3.1vsGrok 4.7DeepSeek V3.1 TerminusvsKimi K3.1 ProMistral Medium 3.1vsKimi K3.1 ProFrequently asked questions
DeepSeek V3.1 Terminus leads Mistral Medium 3.1 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU-Pro). Mistral Medium 3.1 shipped 41 days before DeepSeek V3.1 Terminus, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V3.1 Terminus) vs 128k (Mistral Medium 3.1). DeepSeek V3.1 Terminus is open weight, while Mistral Medium 3.1 is closed.
On GPQA Diamond, DeepSeek V3.1 Terminus leads at 80.7% vs Mistral Medium 3.1 at 65.7%. On MMLU-Pro, DeepSeek V3.1 Terminus leads at 85% vs Mistral Medium 3.1 at 76.8%.