Model comparison
DeepSeek LLM 67B vs Qwen2.5 32B Instruct
Qwen2.5 32B Instruct is the stronger model overall, scoring 30.1 to 24.9 on the Noometry Index.
Last verified . 5 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen2.5 32B Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 32B Instruct leads 24.9 to 7.0.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 56.1% for Qwen2.5 32B Instruct.
Side by side
| DeepSeek LLM 67B | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 30.1 |
| Released | 2023-11-29 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 15 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
DeepSeek LLM 67B: 31.9 (#278), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1096 | — |
| BigCodeBench Complete | — | 52.3% |
Reasoning Qwen2.5 32B Instruct leads
DeepSeek LLM 67B: 16.5 (#304), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| Epoch Capabilities Index | 110.5 | 128.52 |
| LMArena Hard Prompts | 1070 | — |
Math Qwen2.5 32B Instruct leads
DeepSeek LLM 67B: 8.7 (#324), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 7.4% |
| MATH Level 5 | 6.4% | 56.1% |
| LMArena Math | 1108 | — |
Knowledge Qwen2.5 32B Instruct leads
DeepSeek LLM 67B: 7.0 (#313), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 24.6% | 46.1% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), Qwen2.5 32B Instruct: —
| Benchmark | DeepSeek LLM 67B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct is the stronger model overall, scoring 30.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen2.5 32B Instruct better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen2.5 32B Instruct share?
5 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen2.5 32B Instruct has 7.