Model comparison
Deepseek Coder v2 vs Qwen Turbo
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 26.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- The widest gap is in math, where Deepseek Coder v2 leads 32.3 to 14.5.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Qwen Turbo | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 26.8 |
| Released | 2024-06-17 | 2024-11-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 24 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Deepseek Coder v2: 37.5 (#178), Qwen Turbo: —
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Not comparable
Deepseek Coder v2: 22.6 (#175), Qwen Turbo: —
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| LMArena Hard Prompts | 1207 | — |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#188), Qwen Turbo: 14.5 (#291)
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 6.1% |
| LMArena Math | 1241 | — |
| MATH Level 5 | — | 56.2% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 31.7 (#209), Qwen Turbo: 22.2 (#267)
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| GPQA Diamond | — | 41.8% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.4 (#235), Qwen Turbo: —
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.9 (#237), Qwen Turbo: —
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#219), Qwen Turbo: —
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.4 (#249), Qwen Turbo: —
| Benchmark | Deepseek Coder v2 | Qwen Turbo |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1176 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen Turbo?
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 26.8 on the Noometry Index.
How many benchmarks do Deepseek Coder v2 and Qwen Turbo share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen Turbo has 3.