Model comparison
DeepSeek Coder 6.7B vs Qwen3.5 27B
Qwen3.5 27B has enough public results to be ranked (#127); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen3.5 27B leads 38.6 to 35.2.
Side by side
| DeepSeek Coder 6.7B | Qwen3.5 27B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.1 | 41.4 |
| Released | 2023-11-02 | 2026-02-23 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.40 |
| Results tracked | 9 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 27B leads
DeepSeek Coder 6.7B: 35.2 (#216), Qwen3.5 27B: 38.6 (#159)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| LMArena WebDev | — | 1357 |
| WeirdML | — | 39.5% |
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1427 |
| BigCodeBench Complete | 43.8% | — |
| ALE-Bench | — | 349.45 |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: —
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 26.6 (#116)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| NYT Connections (extended) | — | 47.9% |
| Thematic Generalization | — | 45.5% |
| LMArena Hard Prompts | — | 1414 |
| DTBench | — | 82.4% |
| LMCA | — | 34% |
| Epoch Capabilities Index | 88.88 | — |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 36.8 (#103)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 56.7% |
| LMArena Math | — | 1428 |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 37.4 (#149)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| Vectara Hallucination Rate | — | 12.1% |
| LMArena Expert | — | 1428 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Multimodal Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 38.7 (#56)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1240 |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 51.0 (#112)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | — | 1390 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1409 |
| LMArena German | — | 1393 |
| LMArena Japanese | — | 1345 |
| LMArena Korean | — | 1359 |
| LMArena Russian | — | 1389 |
| LMArena Spanish | — | 1408 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 73.7 (#114)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | — | 1393 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 43.1 (#103)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | — | 1413 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Qwen3.5 27B: 59.5 (#106)
| Benchmark | DeepSeek Coder 6.7B | Qwen3.5 27B |
|---|---|---|
| LMArena Text | — | 1409 |
| LMArena Creative Writing | — | 1362 |
| LMArena Multi-Turn | — | 1410 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Qwen3.5 27B?
Qwen3.5 27B has enough public results to be ranked (#127); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Qwen3.5 27B better for coding?
Qwen3.5 27B scores higher on coding benchmarks: 38.6 versus 35.2 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Qwen3.5 27B share?
0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Qwen3.5 27B has 28.