Model comparison
DeepSeek LLM 67B vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Qwen2.5-Coder-32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 7.0.
Side by side
| DeepSeek LLM 67B | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 33.4 |
| Released | 2023-11-29 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 15 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1096 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 16.5 (#304), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1251 |
| Epoch Capabilities Index | 110.5 | 119.49 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 8.7 (#324), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1108 | 1251 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 93% |
Knowledge Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 7.0 (#313), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 29.4 (#267), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1073 | 1205 |
| LMArena Chinese | 1132 | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 55.4 (#277), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 33.1 (#265), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1092 | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
DeepSeek LLM 67B: 31.6 (#282), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1105 | 1230 |
| LMArena Creative Writing | 1067 | 1174 |
| LMArena Multi-Turn | 1082 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen2.5-Coder-32B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 22.6 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen2.5-Coder-32B share?
11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen2.5-Coder-32B has 31.