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 | 400k |
| 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 | $1.25Azure |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.712DeepInfra | $10.00Azure |
| $103StreamLake | $750Azure | |
| 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. | 42% | 77.9% |
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% | — |
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. | — | 58.1% |
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% | — |
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 | OpenAI |
| Release date | Dec 26 2024 | Nov 19 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V3vsClaude Fable 5.2GPT-5.1-Codex-MaxvsClaude Fable 5.2DeepSeek V3vsGemini 4 HydrogenGPT-5.1-Codex-MaxvsGemini 4 HydrogenDeepSeek V3vsMuse EmberGPT-5.1-Codex-MaxvsMuse EmberDeepSeek V3vsGrok 4.7GPT-5.1-Codex-MaxvsGrok 4.7DeepSeek V3vsMistral Large 4GPT-5.1-Codex-MaxvsMistral Large 4DeepSeek V3vsKimi K3.1 ProGPT-5.1-Codex-MaxvsKimi K3.1 ProFrequently asked questions
GPT-5.1-Codex-Max leads DeepSeek V3 on 1 of the 1 benchmark they both report (SWE-Bench Verified). DeepSeek V3 shipped 328 days before GPT-5.1-Codex-Max, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V3) vs 400k (GPT-5.1-Codex-Max). DeepSeek V3 is open weight, while GPT-5.1-Codex-Max is closed.
On SWE-Bench Verified, GPT-5.1-Codex-Max leads at 77.9% vs DeepSeek V3 at 42%.