Model comparison
DeepSeek V4 Pro vs Qwen3.6 Plus
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 47.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 33 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 7 categories and Qwen3.6 Plus in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 29.3.
- The biggest single-benchmark swing is Mystery Game Puzzles: 43% for DeepSeek V4 Pro and 12% for Qwen3.6 Plus.
- DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Qwen3.6 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 54.3 | 47.5 |
| Released | 2026-04-24 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 393K | 66K |
| Input $ / M tokens | $0.66 | $0.50 |
| Output $ / M tokens | $1.98 | $3 |
| Results tracked | 48 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 77.6% | 57.9% |
| LMArena WebDev | 1582 | 1461 |
| SciCode | 51% | 40.7% |
| LMArena Coding | 1470 | 1467 |
| ALE-Bench | 1,403 | 670.15 |
| FrontierCode | 28.6% | — |
| WeirdML | 66.2% | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Qwen3.6 Plus: —
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 3,285 | 5,115 |
| APEX-Agents | 47.3% | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 91.3% | 60.3% |
| CritPt | 18% | 2.9% |
| Chess Puzzles | 47% | 17% |
| LMArena Hard Prompts | 1461 | 1449 |
| Mystery Game Puzzles | 43% | 12% |
| DTBench | 93.9% | 81.9% |
| LMCA | 45.5% | 33.1% |
| Epoch Capabilities Index | 155.31 | 147.65 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| ARC-AGI-1 | 90.5% | — |
| Thematic Generalization | — | 59.5% |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | 38.2% |
| OTIS Mock AIME 2024-2025 | 98.6% | 93.3% |
| LMArena Math | 1455 | 1450 |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 91.7% | 88.4% |
| SimpleQA Verified | 52.9% | 44.1% |
| LMArena Expert | 1464 | 1454 |
| Vectara Hallucination Rate | 8.6% | — |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1439 | 1424 |
| LMArena Chinese | 1486 | 1477 |
| LMArena French | 1472 | 1455 |
| LMArena German | 1458 | 1452 |
| LMArena Japanese | 1445 | 1389 |
| LMArena Korean | 1447 | 1379 |
| LMArena Russian | 1453 | 1434 |
| LMArena Spanish | 1458 | 1432 |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1448 | 1425 |
Long Context Too close to call
DeepSeek V4 Pro: 45.0 (#51), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1458 | 1439 |
| CL-bench | — | 20.3% |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | DeepSeek V4 Pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1451 | 1437 |
| LMArena Creative Writing | 1446 | 1404 |
| LMArena Multi-Turn | 1467 | 1438 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Qwen3.6 Plus?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 47.5 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or Qwen3.6 Plus?
DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is DeepSeek V4 Pro or Qwen3.6 Plus better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do DeepSeek V4 Pro and Qwen3.6 Plus share?
33 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen3.6 Plus has 37.