Model comparison
Deepseek Coder v2 vs Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Qwen3-VL 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-VL 235B-A22B leads 60.2 to 38.2.
Side by side
| Deepseek Coder v2 | Qwen3-VL 235B-A22B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 43.2 |
| Released | 2024-06-17 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 38.1 (#183), Qwen3-VL 235B-A22B: 42.4 (#100)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Coding | 1251 | 1439 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 23.6 (#176), Qwen3-VL 235B-A22B: 29.3 (#92)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1428 |
| WinoGrande | 83.7% | — |
Math Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 34.9 (#190), Qwen3-VL 235B-A22B: 39.0 (#118)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | 1241 | 1426 |
| GSM8K | 94.5% | — |
Knowledge Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 32.3 (#212), Qwen3-VL 235B-A22B: 40.3 (#121)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Expert | 1181 | 1442 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Qwen3-VL 235B-A22B: 39.8 (#55)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 36.3 (#240), Qwen3-VL 235B-A22B: 51.9 (#97)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | 1182 | 1405 |
| LMArena Chinese | 1201 | 1463 |
| LMArena French | 1185 | 1452 |
| LMArena German | 1164 | 1424 |
| LMArena Japanese | 1126 | 1385 |
| LMArena Korean | 1104 | 1394 |
| LMArena Russian | 1188 | 1408 |
| LMArena Spanish | 1153 | 1428 |
Instruction Following Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 61.7 (#242), Qwen3-VL 235B-A22B: 74.2 (#101)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1406 |
Long Context Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 37.0 (#224), Qwen3-VL 235B-A22B: 43.4 (#98)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1219 | 1420 |
Writing & Preference Qwen3-VL 235B-A22B leads
Deepseek Coder v2: 38.2 (#253), Qwen3-VL 235B-A22B: 60.2 (#99)
| Benchmark | Deepseek Coder v2 | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | 1191 | 1420 |
| LMArena Creative Writing | 1120 | 1366 |
| LMArena Multi-Turn | 1177 | 1428 |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Qwen3-VL 235B-A22B better for coding?
Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Qwen3-VL 235B-A22B share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3-VL 235B-A22B has 18.