Model comparison
DeepSeek-R1 vs Qwen3.6 Flash
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 38.8 on the Noometry Index. Qwen3.6 Flash costs 2.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and Qwen3.6 Flash in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Flash leads 29.0 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 84.4% for Qwen3.6 Flash.
- Qwen3.6 Flash is cheaper at $0.19 / $1.13 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Qwen3.6 Flash accepts more context: 1M tokens versus 164K.
Side by side
| DeepSeek-R1 | Qwen3.6 Flash | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.3 | 38.8 |
| Released | 2025-01-20 | 2026-04-27 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1M |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $0.19 |
| Output $ / M tokens | $2.15 | $1.13 |
| Results tracked | 52 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-R1: 46.3 (#68), Qwen3.6 Flash: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| ALE-Bench | 804.12 | 326.4 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| LMArena Coding | 1427 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Qwen3.6 Flash: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Qwen3.6 Flash leads
DeepSeek-R1: 18.6 (#278), Qwen3.6 Flash: 29.0 (#96)
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| SimpleBench | 40.8% | 35.2% |
| Epoch Capabilities Index | 141.29 | 143.26 |
| ARC-AGI-2 | 1.3% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 83.2% | — |
| LMArena Hard Prompts | 1416 | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 77.1% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 31% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Qwen3.6 Flash: 39.0 (#117)
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 84.4% |
| FrontierMath (Tiers 1-3) | — | 22.5% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| LMArena Math | 1400 | — |
| MATH Level 5 | 96.6% | — |
| FrontierMath (Feb 2025 set) | — | 10.3% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Qwen3.6 Flash: 42.1 (#100)
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| GPQA Diamond | 76.3% | 83.3% |
| SimpleQA Verified | — | 15.9% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
| LMArena Expert | 1394 | — |
Multilingual Not comparable
DeepSeek-R1: 52.4 (#85), Qwen3.6 Flash: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| LMArena Non-English | 1412 | — |
| LMArena Chinese | 1442 | — |
| LMArena French | 1417 | — |
| LMArena German | 1404 | — |
| LMArena Japanese | 1391 | — |
| LMArena Korean | 1360 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1411 | — |
Instruction Following Not comparable
DeepSeek-R1: 72.0 (#143), Qwen3.6 Flash: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
| LMArena Instruction Following | 1382 | — |
Long Context Not comparable
DeepSeek-R1: 45.4 (#36), Qwen3.6 Flash: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| Fiction.LiveBench | 75% | — |
| LMArena Longer Query | 1391 | — |
Writing & Preference Not comparable
DeepSeek-R1: 61.4 (#88), Qwen3.6 Flash: —
| Benchmark | DeepSeek-R1 | Qwen3.6 Flash |
|---|---|---|
| LMArena Text | 1428 | — |
| LMArena Creative Writing | 1405 | — |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LMArena Multi-Turn | 1405 | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Qwen3.6 Flash?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 38.8 on the Noometry Index. Qwen3.6 Flash costs 2.2× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Qwen3.6 Flash?
Qwen3.6 Flash is cheaper. It lists at $0.19 per million input tokens and $1.13 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Which has the bigger context window?
Qwen3.6 Flash does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-R1 and Qwen3.6 Flash share?
5 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen3.6 Flash has 13.