Model comparison
DeepSeek LLM 67B vs Qwen Turbo
Qwen Turbo is the stronger model overall, scoring 26.8 to 24.8 on the Noometry Index.
Last verified . 3 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen Turbo in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Turbo leads 22.2 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 56.2% for Qwen Turbo.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Qwen Turbo | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 26.8 |
| Released | 2023-11-29 | 2024-11-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 15 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek LLM 67B: 31.3 (#273), Qwen Turbo: —
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| LMArena Coding | 1096 | — |
Reasoning Not comparable
DeepSeek LLM 67B: 15.9 (#300), Qwen Turbo: —
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.54 | — |
Math Qwen Turbo leads
DeepSeek LLM 67B: 8.1 (#318), Qwen Turbo: 14.5 (#291)
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 6.1% |
| MATH Level 5 | 6.4% | 56.2% |
| LMArena Math | 1108 | — |
Knowledge Qwen Turbo leads
DeepSeek LLM 67B: 7.1 (#308), Qwen Turbo: 22.2 (#267)
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| GPQA Diamond | 24.6% | 41.8% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.5 (#262), Qwen Turbo: —
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.7 (#272), Qwen Turbo: —
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#260), Qwen Turbo: —
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.8 (#277), Qwen Turbo: —
| Benchmark | DeepSeek LLM 67B | Qwen Turbo |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen Turbo?
Qwen Turbo is the stronger model overall, scoring 26.8 to 24.8 on the Noometry Index.
How many benchmarks do DeepSeek LLM 67B and Qwen Turbo share?
3 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen Turbo has 3.