Model comparison
DeepSeek-R1 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 42.3 on the Noometry Index. DeepSeek-R1 costs 3.2× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. DeepSeek-R1 scores higher in 1 category and Qwen3.6 Max Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Max Preview leads 41.7 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 91.1% for Qwen3.6 Max Preview.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-R1 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.3 | 51.5 |
| Released | 2025-01-20 | 2026-04-20 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $1.30 |
| Output $ / M tokens | $2.15 | $7.80 |
| Results tracked | 52 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
DeepSeek-R1: 46.3 (#68), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1427 | 1471 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1482 |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Qwen3.6 Max Preview: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
DeepSeek-R1: 18.6 (#278), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 40.8% | 63% |
| LMArena Hard Prompts | 1416 | 1457 |
| Epoch Capabilities Index | 141.29 | 149.24 |
| ARC-AGI-2 | 1.3% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 74.1% |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 83.2% | — |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 42.5% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Qwen3.6 Max Preview leads
DeepSeek-R1: 43.8 (#79), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 91.1% |
| LMArena Math | 1400 | 1465 |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
DeepSeek-R1: 44.5 (#87), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 76.3% | 87.4% |
| LMArena Expert | 1394 | 1478 |
| SimpleQA Verified | — | 52% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual Qwen3.6 Max Preview leads
DeepSeek-R1: 52.4 (#85), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1412 | 1437 |
| LMArena Chinese | 1442 | 1487 |
| LMArena French | 1417 | 1449 |
| LMArena Russian | 1423 | 1445 |
| LMArena Spanish | 1411 | 1454 |
| LMArena German | 1404 | — |
| LMArena Japanese | 1391 | — |
| LMArena Korean | 1360 | — |
Instruction Following Qwen3.6 Max Preview leads
DeepSeek-R1: 72.0 (#143), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1382 | 1438 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context Too close to call
DeepSeek-R1: 45.4 (#36), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1391 | 1457 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Qwen3.6 Max Preview leads
DeepSeek-R1: 61.4 (#88), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | DeepSeek-R1 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1428 | 1447 |
| LMArena Creative Writing | 1405 | 1435 |
| LMArena Multi-Turn | 1405 | 1456 |
| 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 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 42.3 on the Noometry Index. DeepSeek-R1 costs 3.2× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Qwen3.6 Max Preview?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is DeepSeek-R1 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-R1 and Qwen3.6 Max Preview share?
18 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen3.6 Max Preview has 29.