Model comparison
Deepseek Coder v2 vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 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 Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.6 Plus leads 62.2 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Qwen3.6 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 47.5 |
| Released | 2024-06-17 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 24 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Deepseek Coder v2: 38.1 (#183), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1251 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 670.15 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Qwen3.6 Plus: —
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
Deepseek Coder v2: 23.6 (#176), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1449 |
| NYT Connections (extended) | — | 60.3% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
| Epoch Capabilities Index | — | 147.65 |
| WinoGrande | 83.7% | — |
Math Qwen3.6 Plus leads
Deepseek Coder v2: 34.9 (#190), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1241 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
| GSM8K | 94.5% | — |
Knowledge Qwen3.6 Plus leads
Deepseek Coder v2: 32.3 (#212), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1181 | 1454 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Qwen3.6 Plus leads
Deepseek Coder v2: 36.3 (#240), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1182 | 1424 |
| LMArena Chinese | 1201 | 1477 |
| LMArena French | 1185 | 1455 |
| LMArena German | 1164 | 1452 |
| LMArena Japanese | 1126 | 1389 |
| LMArena Korean | 1104 | 1379 |
| LMArena Russian | 1188 | 1434 |
| LMArena Spanish | 1153 | 1432 |
Instruction Following Qwen3.6 Plus leads
Deepseek Coder v2: 61.7 (#242), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1180 | 1425 |
Long Context Qwen3.6 Plus leads
Deepseek Coder v2: 37.0 (#224), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1219 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
Deepseek Coder v2: 38.2 (#253), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Deepseek Coder v2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1191 | 1437 |
| LMArena Creative Writing | 1120 | 1404 |
| LMArena Multi-Turn | 1177 | 1438 |
Frequently asked questions
Is Deepseek Coder v2 better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Qwen3.6 Plus share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.6 Plus has 37.