Model comparison
DeepSeek-R1 vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and Qwen3.6 Plus in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 44.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 93.3% for Qwen3.6 Plus.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 164K.
Side by side
| DeepSeek-R1 | Qwen3.6 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.3 | 47.5 |
| Released | 2025-01-20 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1M |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $0.50 |
| Output $ / M tokens | $2.15 | $3 |
| Results tracked | 52 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| SciCode | 35.7% | 40.7% |
| LMArena Coding | 1427 | 1467 |
| ALE-Bench | 804.12 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1461 |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Qwen3.6 Plus: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
DeepSeek-R1: 18.6 (#278), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| CritPt | 1.1% | 2.9% |
| LMArena Hard Prompts | 1416 | 1449 |
| Epoch Capabilities Index | 141.29 | 147.65 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 21.2% | — |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| LiveBench Reasoning | 83.2% | — |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 33.1% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Qwen3.6 Plus leads
DeepSeek-R1: 43.8 (#79), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 93.3% |
| LMArena Math | 1400 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
DeepSeek-R1: 44.5 (#87), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 76.3% | 88.4% |
| LMArena Expert | 1394 | 1454 |
| SimpleQA Verified | — | 44.1% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual Too close to call
DeepSeek-R1: 52.4 (#85), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1412 | 1424 |
| LMArena Chinese | 1442 | 1477 |
| LMArena French | 1417 | 1455 |
| LMArena German | 1404 | 1452 |
| LMArena Japanese | 1391 | 1389 |
| LMArena Korean | 1360 | 1379 |
| LMArena Russian | 1423 | 1434 |
| LMArena Spanish | 1411 | 1432 |
Instruction Following Qwen3.6 Plus leads
DeepSeek-R1: 72.0 (#143), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1382 | 1425 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context Too close to call
DeepSeek-R1: 45.4 (#36), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1391 | 1439 |
| Fiction.LiveBench | 75% | — |
| CL-bench | — | 20.3% |
Writing & Preference Too close to call
DeepSeek-R1: 61.4 (#88), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | DeepSeek-R1 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1428 | 1437 |
| LMArena Creative Writing | 1405 | 1404 |
| LMArena Multi-Turn | 1405 | 1438 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.3 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or Qwen3.6 Plus?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is DeepSeek-R1 or Qwen3.6 Plus better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-R1 and Qwen3.6 Plus share?
23 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen3.6 Plus has 37.