Model comparison
DeepSeek-V3 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 39.5 on the Noometry Index. DeepSeek-V3 costs 7.2× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. DeepSeek-V3 scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 32.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for DeepSeek-V3 and 91.1% for Qwen3.6 Max Preview.
- DeepSeek-V3 is cheaper at $0.24 / $0.90 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.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 39.5 | 51.5 |
| Released | 2024-12-26 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 164K | 262K |
| Max output | 164K | 66K |
| Input $ / M tokens | $0.24 | $1.30 |
| Output $ / M tokens | $0.90 | $7.80 |
| Results tracked | 60 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
DeepSeek-V3: 42.3 (#106), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1368 | 1471 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1482 |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Qwen3.6 Max Preview: —
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| METR Time Horizons | 49.6% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
DeepSeek-V3: 20.5 (#236), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 27.2% | 63% |
| LMArena Hard Prompts | 1365 | 1457 |
| DTBench | 64.8% | 87.2% |
| LMCA | 15.5% | 42.5% |
| Epoch Capabilities Index | 135.94 | 149.24 |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 0% | — |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 65.8% | — |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | 60.9% | — |
| BIG-Bench Hard | 87.5% | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math Qwen3.6 Max Preview leads
DeepSeek-V3: 32.1 (#219), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 91.1% |
| LMArena Math | 1373 | 1465 |
| FrontierMath (Feb 2025 set) | 1.7% | 23.1% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
DeepSeek-V3: 37.5 (#155), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 67.6% | 87.4% |
| LMArena Expert | 1351 | 1478 |
| SimpleQA Verified | — | 52% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual Qwen3.6 Max Preview leads
DeepSeek-V3: 48.5 (#143), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1358 | 1437 |
| LMArena Chinese | 1391 | 1487 |
| LMArena French | 1385 | 1449 |
| LMArena Russian | 1373 | 1445 |
| LMArena Spanish | 1358 | 1454 |
| LMArena German | 1374 | — |
| LMArena Japanese | 1333 | — |
| LMArena Korean | 1319 | — |
Instruction Following Qwen3.6 Max Preview leads
DeepSeek-V3: 72.8 (#130), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1345 | 1438 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context Qwen3.6 Max Preview leads
DeepSeek-V3: 34.0 (#253), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1352 | 1457 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Qwen3.6 Max Preview leads
DeepSeek-V3: 57.4 (#130), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | DeepSeek-V3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1375 | 1447 |
| LMArena Creative Writing | 1364 | 1435 |
| LMArena Multi-Turn | 1389 | 1456 |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 39.5 on the Noometry Index. DeepSeek-V3 costs 7.2× 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-V3 or Qwen3.6 Max Preview?
DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is DeepSeek-V3 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 42.3 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-V3 and Qwen3.6 Max Preview share?
21 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Qwen3.6 Max Preview has 29.