Model comparison
DeepSeek V4.1 Flash vs Qwen3.6 Plus
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 47.3 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 6 categories and Qwen3.6 Plus in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 28.5.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 60.3% for Qwen3.6 Plus.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Qwen3.6 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 50.3 | 47.3 |
| Released | 2026-09-09 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 393K | 66K |
| Input $ / M tokens | $0.15 | $0.50 |
| Output $ / M tokens | $0.60 | $3 |
| Results tracked | 25 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.8 (#29), Qwen3.6 Plus: 40.6 (#125)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1620 | 1461 |
| SciCode | 51.9% | 40.7% |
| LMArena Coding | 1511 | 1467 |
| ALE-Bench | 1,092 | 670.15 |
| SWE-bench Verified | — | 57.9% |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: —, Qwen3.6 Plus: —
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 46.2 (#39), Qwen3.6 Plus: 28.5 (#89)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 89.6% | 60.3% |
| CritPt | 14.3% | 2.9% |
| LMArena Hard Prompts | 1485 | 1449 |
| DTBench | 89.9% | 81.9% |
| LMCA | 47% | 33.1% |
| Epoch Capabilities Index | 155.01 | 147.67 |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| Surface Evolver Bench | 46.3% | — |
Math Qwen3.6 Plus leads
DeepSeek V4.1 Flash: 48.4 (#52), Qwen3.6 Plus: 50.6 (#44)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1493 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | 54% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
DeepSeek V4.1 Flash: 41.6 (#97), Qwen3.6 Plus: 56.1 (#40)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1505 | 1456 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.5 (#29), Qwen3.6 Plus: 53.5 (#66)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1452 | 1424 |
| LMArena Chinese | 1506 | 1478 |
| LMArena French | 1448 | 1454 |
| LMArena Russian | 1473 | 1434 |
| LMArena Spanish | 1499 | 1432 |
| LMArena German | — | 1451 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1381 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.6 (#24), Qwen3.6 Plus: 75.2 (#70)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1475 | 1425 |
Long Context Too close to call
DeepSeek V4.1 Flash: 45.2 (#46), Qwen3.6 Plus: 45.1 (#48)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1476 | 1440 |
| CL-bench | — | 20.3% |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.8 (#43), Qwen3.6 Plus: 62.4 (#78)
| Benchmark | DeepSeek V4.1 Flash | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1465 | 1437 |
| LMArena Creative Writing | 1436 | 1405 |
| LMArena Multi-Turn | 1460 | 1438 |
| EQ-Bench Creative Writing | 1540 | — |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Qwen3.6 Plus?
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 47.3 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or Qwen3.6 Plus?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is DeepSeek V4.1 Flash or Qwen3.6 Plus better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 40.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do DeepSeek V4.1 Flash and Qwen3.6 Plus share?
22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Qwen3.6 Plus has 37.