Model comparison
DeepSeek-V3.1 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Qwen3.5 Max Preview leads 45.2 to 36.3.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 45.3 |
| Released | 2025-08-21 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
DeepSeek-V3.1: 40.3 (#144), Qwen3.5 Max Preview: 44.0 (#77)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1417 | 1487 |
| WeirdML | 38.4% | — |
Reasoning Qwen3.5 Max Preview leads
DeepSeek-V3.1: 27.9 (#110), Qwen3.5 Max Preview: 30.8 (#84)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1483 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Qwen3.5 Max Preview leads
DeepSeek-V3.1: 38.9 (#122), Qwen3.5 Max Preview: 40.1 (#94)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1420 | 1474 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Qwen3.5 Max Preview: 41.8 (#107)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1405 | 1489 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual Qwen3.5 Max Preview leads
DeepSeek-V3.1: 51.6 (#106), Qwen3.5 Max Preview: 56.2 (#22)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1400 | 1465 |
| LMArena Chinese | 1469 | 1534 |
| LMArena French | 1447 | 1484 |
| LMArena German | 1411 | 1487 |
| LMArena Japanese | 1378 | 1495 |
| LMArena Korean | 1337 | 1438 |
| LMArena Russian | 1405 | 1471 |
| LMArena Spanish | 1431 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
DeepSeek-V3.1: 73.9 (#110), Qwen3.5 Max Preview: 77.0 (#31)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1400 | 1467 |
Long Context Qwen3.5 Max Preview leads
DeepSeek-V3.1: 36.3 (#232), Qwen3.5 Max Preview: 45.2 (#45)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1422 | 1476 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference Qwen3.5 Max Preview leads
DeepSeek-V3.1: 60.3 (#98), Qwen3.5 Max Preview: 66.0 (#41)
| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1420 | 1470 |
| LMArena Creative Writing | 1401 | 1464 |
| LMArena Multi-Turn | 1408 | 1478 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index.
Is DeepSeek-V3.1 or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 40.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3.5 Max Preview has 17.