Model comparison
Deepseek Coder v2 vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 35.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Deepseek Coder v2 scores higher in 2 categories and Qwen Plus in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Qwen Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 37.1 |
| Released | 2024-06-17 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 24 | 20 |
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), Qwen Plus: 38.9 (#167)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Coding | 1251 | 1328 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Qwen Plus leads
Deepseek Coder v2: 23.6 (#176), Qwen Plus: 28.4 (#107)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1317 |
| Kagi LLM Benchmark | — | 63.3% |
| DTBench | — | 81.1% |
| LMCA | — | 24% |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Qwen Plus: 23.3 (#271)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Math | 1241 | 1326 |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), Qwen Plus: 27.4 (#251)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Expert | 1181 | 1328 |
| GPQA Diamond | — | 48.1% |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Qwen Plus leads
Deepseek Coder v2: 36.3 (#240), Qwen Plus: 45.1 (#175)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1182 | 1310 |
| LMArena Chinese | 1201 | 1347 |
| LMArena Japanese | 1126 | 1251 |
| LMArena Russian | 1188 | 1323 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Qwen Plus leads
Deepseek Coder v2: 61.7 (#242), Qwen Plus: 68.8 (#181)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1180 | 1303 |
Long Context Qwen Plus leads
Deepseek Coder v2: 37.0 (#224), Qwen Plus: 40.3 (#158)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1219 | 1324 |
Writing & Preference Qwen Plus leads
Deepseek Coder v2: 38.2 (#253), Qwen Plus: 52.2 (#176)
| Benchmark | Deepseek Coder v2 | Qwen Plus |
|---|---|---|
| LMArena Text | 1191 | 1326 |
| LMArena Creative Writing | 1120 | 1293 |
| LMArena Multi-Turn | 1177 | 1336 |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Qwen Plus better for coding?
They score almost the same on coding (38.1 vs 38.9); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Qwen Plus share?
13 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen Plus has 20.