Model comparison
Deepseek Coder v2 vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 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 Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 38.2.
Side by side
| Deepseek Coder v2 | Qwen3.8 27B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 46.0 |
| Released | 2024-06-17 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 24 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Deepseek Coder v2: 38.1 (#183), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1251 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Deepseek Coder v2: 23.6 (#176), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
| WinoGrande | 83.7% | — |
Math Qwen3.8 27B leads
Deepseek Coder v2: 34.9 (#190), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1241 | 1456 |
| ProofBench | — | 16% |
| GSM8K | 94.5% | — |
Knowledge Qwen3.8 27B leads
Deepseek Coder v2: 32.3 (#212), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1181 | 1482 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Deepseek Coder v2: 36.3 (#240), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1182 | 1430 |
| LMArena Chinese | 1201 | 1504 |
| LMArena French | 1185 | 1465 |
| LMArena German | 1164 | 1438 |
| LMArena Japanese | 1126 | 1384 |
| LMArena Korean | 1104 | 1393 |
| LMArena Russian | 1188 | 1415 |
| LMArena Spanish | 1153 | 1448 |
Instruction Following Qwen3.8 27B leads
Deepseek Coder v2: 61.7 (#242), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1439 |
Long Context Qwen3.8 27B leads
Deepseek Coder v2: 37.0 (#224), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1219 | 1450 |
Writing & Preference Qwen3.8 27B leads
Deepseek Coder v2: 38.2 (#253), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Deepseek Coder v2 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1191 | 1441 |
| LMArena Creative Writing | 1120 | 1384 |
| LMArena Multi-Turn | 1177 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Qwen3.8 27B share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.8 27B has 31.