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 | 2.4T |
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 | 1M |
| 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. | — | $2.00Alibaba |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $6.00Alibaba |
| — | $700Alibaba | |
| 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. | 49.2% | — |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 69.3% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 64.9% |
QwenSWEBench V2Software engineering — Qwen's in-house coding benchmark, second version, built around complex real-world software-engineering tasks. Scores are not comparable with the first version. Higher is better. | — | 70% |
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 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | — | 26.97% |
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | — | 29% |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 64% |
CoWorkBenchLong-horizon office work — Tests long-running office tasks across fields including computer science, finance, law, medicine, and other productivity work. Higher is better. | — | 76.1% |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | — | 73.3% |
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% | — |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | — | 50.8% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 82.7% |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Jan 20 2025 | Sep 2 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek R1vsClaude Fable 5.2Qwen3.8-Max-0902vsClaude Fable 5.2DeepSeek R1vsGPT-6.2 AstraQwen3.8-Max-0902vsGPT-6.2 AstraDeepSeek R1vsGemini 4 HydrogenQwen3.8-Max-0902vsGemini 4 HydrogenDeepSeek R1vsMuse EmberQwen3.8-Max-0902vsMuse EmberDeepSeek R1vsGrok 4.7Qwen3.8-Max-0902vsGrok 4.7DeepSeek R1vsMistral Large 4Qwen3.8-Max-0902vsMistral Large 4Frequently asked questions
DeepSeek R1 and Qwen3.8-Max-0902 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek R1 shipped 590 days before Qwen3.8-Max-0902, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 has 671B parameters, while Qwen3.8-Max-0902 has 2.4T. Context windows are 128k (DeepSeek R1) vs 1M (Qwen3.8-Max-0902). DeepSeek R1 is open weight, while Qwen3.8-Max-0902 is closed.
Direct benchmark comparisons are unavailable — DeepSeek R1 and Qwen3.8-Max-0902 don't publish scores on any of the same benchmarks.