Model comparison
Deepseek Coder v2 vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 35.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Qwen2.5 Plus 1127 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 Plus 1127 leads 49.4 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 38.8 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 38.1 (#183), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1251 | 1314 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 23.6 (#176), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1299 |
| WinoGrande | 83.7% | — |
Math Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 34.9 (#190), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1241 | 1298 |
| GSM8K | 94.5% | — |
Knowledge Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 32.3 (#212), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1181 | 1289 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 36.3 (#240), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1182 | 1265 |
| LMArena Chinese | 1201 | 1314 |
| LMArena German | 1164 | 1231 |
| LMArena Japanese | 1126 | 1207 |
| LMArena Russian | 1188 | 1271 |
| LMArena French | 1185 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 61.7 (#242), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1275 |
Long Context Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 37.0 (#224), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1219 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Deepseek Coder v2: 38.2 (#253), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | Deepseek Coder v2 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1191 | 1299 |
| LMArena Creative Writing | 1120 | 1262 |
| LMArena Multi-Turn | 1177 | 1299 |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Qwen2.5 Plus 1127 better for coding?
They score almost the same on coding (38.1 vs 38.5); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen2.5 Plus 1127 has 14.