Model comparison
DeepSeek LLM 67B vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 30.8 to 24.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 4 categories and Qwen1.5-7B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-7B leads 28.2 to 7.1.
Side by side
| DeepSeek LLM 67B | Qwen1.5-7B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 30.8 |
| Released | 2023-11-29 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek LLM 67B: 31.3 (#273), Qwen1.5-7B: 31.6 (#271)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1096 | 1107 |
Reasoning Qwen1.5-7B leads
DeepSeek LLM 67B: 15.9 (#300), Qwen1.5-7B: 19.5 (#237)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1066 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Qwen1.5-7B leads
DeepSeek LLM 67B: 8.1 (#318), Qwen1.5-7B: 29.0 (#222)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1108 | 1080 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen1.5-7B leads
DeepSeek LLM 67B: 7.1 (#308), Qwen1.5-7B: 28.2 (#239)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1055 |
| MMLU | — | 62.6% |
Multilingual Too close to call
DeepSeek LLM 67B: 29.5 (#262), Qwen1.5-7B: 28.6 (#266)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1073 | 1058 |
| LMArena Chinese | 1132 | 1140 |
| LMArena Russian | — | 1006 |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.7 (#272), Qwen1.5-7B: 54.4 (#276)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1058 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#260), Qwen1.5-7B: 33.1 (#261)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1092 | 1090 |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.8 (#277), Qwen1.5-7B: 29.8 (#288)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1105 | 1084 |
| LMArena Creative Writing | 1067 | 1035 |
| LMArena Multi-Turn | 1082 | 1061 |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 30.8 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen1.5-7B better for coding?
They score almost the same on coding (31.3 vs 31.6); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Qwen1.5-7B share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen1.5-7B has 13.