Model comparison
DeepSeek LLM 67B vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 24.8 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Qwen2.5 7B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 31.8.
- The biggest single-benchmark swing is GPQA Diamond: 24.6% for DeepSeek LLM 67B and 35.5% for Qwen2.5 7B Instruct.
Side by side
| DeepSeek LLM 67B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 28.6 |
| Released | 2023-11-29 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 15 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
DeepSeek LLM 67B: 31.3 (#273), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1096 | — |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 15.9 (#300), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| Epoch Capabilities Index | 110.54 | 118.44 |
| LMArena Hard Prompts | 1070 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
Math Qwen2.5 7B Instruct leads
DeepSeek LLM 67B: 8.1 (#318), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen2.5 7B Instruct leads
DeepSeek LLM 67B: 7.1 (#308), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 24.6% | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.5 (#262), Qwen2.5 7B Instruct: —
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Qwen2.5 7B Instruct leads
DeepSeek LLM 67B: 55.7 (#272), Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#260), Qwen2.5 7B Instruct: —
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Qwen2.5 7B Instruct leads
DeepSeek LLM 67B: 31.8 (#277), Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen2.5 7B Instruct share?
4 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen2.5 7B Instruct has 15.