Model comparison
Deepseek Coder v2 vs Qwen1.5-32B
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Deepseek Coder v2 scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Deepseek Coder v2 leads 31.7 to 13.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 42% for Qwen1.5-32B.
Side by side
| Deepseek Coder v2 | Qwen1.5-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 30.0 |
| Released | 2024-06-17 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 37.5 (#178), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 32.3% |
| LMArena Coding | 1251 | 1155 |
| BigCodeBench Complete | 59.7% | 42% |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 22.6 (#175), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1131 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#188), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1241 | 1155 |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 31.7 (#209), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1181 | 1126 |
| GPQA Diamond | — | 30.7% |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 74.4% |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.4 (#235), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1182 | 1106 |
| LMArena Chinese | 1201 | 1176 |
| LMArena French | 1184 | 1100 |
| LMArena German | 1164 | 1058 |
| LMArena Japanese | 1126 | 1027 |
| LMArena Korean | 1104 | 1007 |
| LMArena Russian | 1188 | 1073 |
| LMArena Spanish | 1153 | 1089 |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.9 (#237), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1116 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#219), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1219 | 1146 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.4 (#249), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Deepseek Coder v2 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1191 | 1137 |
| LMArena Creative Writing | 1120 | 1083 |
| LMArena Multi-Turn | 1176 | 1140 |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen1.5-32B?
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.0 on the Noometry Index.
Is Deepseek Coder v2 or Qwen1.5-32B better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 31.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Qwen1.5-32B share?
19 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen1.5-32B has 21.