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 | ||
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% | 61.6% |
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% | — |
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% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 85% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Sep 22 2025 | Jul 10 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1 TerminusvsClaude Fable 5.2Devstral MediumvsClaude Fable 5.2DeepSeek V3.1 TerminusvsGPT-6.2 AstraDevstral MediumvsGPT-6.2 AstraDeepSeek V3.1 TerminusvsGemini 4 HydrogenDevstral MediumvsGemini 4 HydrogenDeepSeek V3.1 TerminusvsMuse EmberDevstral MediumvsMuse EmberDeepSeek V3.1 TerminusvsGrok 4.7Devstral MediumvsGrok 4.7DeepSeek V3.1 TerminusvsKimi K3.1 ProDevstral MediumvsKimi K3.1 ProFrequently asked questions
DeepSeek V3.1 Terminus leads Devstral Medium on 1 of the 1 benchmark they both report (SWE-Bench Verified). Devstral Medium shipped 74 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 (Devstral Medium). DeepSeek V3.1 Terminus is open weight, while Devstral Medium is closed.
On SWE-Bench Verified, DeepSeek V3.1 Terminus leads at 68.4% vs Devstral Medium at 61.6%.