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. | 236B | 7B |
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 | 64k |
| Benchmarks | ||
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. | 89% | 83.5% |
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. | 16.8% | — |
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. | 41.8% | — |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Sep 5 2024 | Apr 16 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Fable 5.2CodeQwen1.5vsClaude Fable 5.2DeepSeek V2.5vsGPT-6.2 AstraCodeQwen1.5vsGPT-6.2 AstraDeepSeek V2.5vsGemini 4 NeonCodeQwen1.5vsGemini 4 NeonDeepSeek V2.5vsMuse EmberCodeQwen1.5vsMuse EmberDeepSeek V2.5vsGrok 4.7CodeQwen1.5vsGrok 4.7DeepSeek V2.5vsMistral Large 4CodeQwen1.5vsMistral Large 4Frequently asked questions
DeepSeek V2.5 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 142 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 has 236B parameters, while CodeQwen1.5 has 7B. Context windows are 128k (DeepSeek V2.5) vs 64k (CodeQwen1.5).
On HumanEval, DeepSeek V2.5 leads at 89% vs CodeQwen1.5 at 83.5%.