Model comparison
Deepseek Coder v2 vs Qwen3.6 27B
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 35.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- The widest gap is in knowledge, where Qwen3.6 27B leads 52.4 to 32.3.
Side by side
| Deepseek Coder v2 | Qwen3.6 27B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 42.2 |
| Released | 2024-06-17 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 24 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 27B leads
Deepseek Coder v2: 38.1 (#183), Qwen3.6 27B: 39.1 (#163)
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| SciCode | — | 37.3% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Qwen3.6 27B leads
Deepseek Coder v2: 23.6 (#176), Qwen3.6 27B: 25.0 (#153)
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| CritPt | — | 0.9% |
| Chess Puzzles | — | 22% |
| LMArena Hard Prompts | 1207 | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 78.1% |
| LMCA | — | 34.5% |
| Epoch Capabilities Index | — | 146.5 |
| WinoGrande | 83.7% | — |
Math Qwen3.6 27B leads
Deepseek Coder v2: 34.9 (#190), Qwen3.6 27B: 48.5 (#62)
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 35.1% |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Qwen3.6 27B leads
Deepseek Coder v2: 32.3 (#212), Qwen3.6 27B: 52.4 (#63)
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | — | 85.9% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), Qwen3.6 27B: —
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.7 (#242), Qwen3.6 27B: —
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Qwen3.6 27B: —
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Qwen3.6 27B leads
Deepseek Coder v2: 38.2 (#253), Qwen3.6 27B: 50.3 (#181)
| Benchmark | Deepseek Coder v2 | Qwen3.6 27B |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| EQ-Bench 4 | — | 1026 |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen3.6 27B?
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Qwen3.6 27B better for coding?
Qwen3.6 27B scores higher on coding benchmarks: 39.1 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Qwen3.6 27B share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.6 27B has 11.