Model comparison
DeepSeek-V3.1 vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 2.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 38.9.
- The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 33.1% for Qwen3.6 Plus.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Qwen3.6 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 47.5 |
| Released | 2025-08-21 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.25 | $0.50 |
| Output $ / M tokens | $0.95 | $3 |
| Results tracked | 27 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1: 40.3 (#144), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1417 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| WeirdML | 38.4% | — |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Qwen3.6 Plus: —
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
DeepSeek-V3.1: 27.9 (#110), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1449 |
| DTBench | 82.7% | 81.9% |
| LMCA | 24.3% | 33.1% |
| Epoch Capabilities Index | 139.92 | 147.65 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 60.3% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| ForecastBench | 58 | — |
Math Qwen3.6 Plus leads
DeepSeek-V3.1: 38.9 (#122), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1420 | 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% |
Knowledge Qwen3.6 Plus leads
DeepSeek-V3.1: 43.7 (#90), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1405 | 1454 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual Qwen3.6 Plus leads
DeepSeek-V3.1: 51.6 (#106), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1400 | 1424 |
| LMArena Chinese | 1469 | 1477 |
| LMArena French | 1447 | 1455 |
| LMArena German | 1411 | 1452 |
| LMArena Japanese | 1378 | 1389 |
| LMArena Korean | 1337 | 1379 |
| LMArena Russian | 1405 | 1434 |
| LMArena Spanish | 1431 | 1432 |
Instruction Following Qwen3.6 Plus leads
DeepSeek-V3.1: 73.9 (#110), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1400 | 1425 |
Long Context Qwen3.6 Plus leads
DeepSeek-V3.1: 36.3 (#232), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1422 | 1439 |
| Fiction.LiveBench | 52.8% | — |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
DeepSeek-V3.1: 60.3 (#98), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | DeepSeek-V3.1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1420 | 1437 |
| LMArena Creative Writing | 1401 | 1404 |
| LMArena Multi-Turn | 1408 | 1438 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 2.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1 or Qwen3.6 Plus?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is DeepSeek-V3.1 or Qwen3.6 Plus better for coding?
They score almost the same on coding (40.3 vs 40.8); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Qwen3.6 Plus share?
20 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3.6 Plus has 37.