Model comparison
DeepSeek-V3.1 vs Qwen1.5-32B
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.5 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 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 13.5.
Side by side
| DeepSeek-V3.1 | Qwen1.5-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 30.5 |
| Released | 2025-08-21 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Qwen1.5-32B: 31.7 (#282)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1417 | 1155 |
| WeirdML | 38.4% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Qwen1.5-32B: 21.8 (#212)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1130 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Qwen1.5-32B: 33.0 (#207)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1420 | 1155 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Qwen1.5-32B: 13.5 (#296)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1405 | 1126 |
| GPQA Diamond | — | 30.7% |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | — | 74.4% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Qwen1.5-32B: 31.4 (#259)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1400 | 1106 |
| LMArena Chinese | 1469 | 1177 |
| LMArena French | 1447 | 1101 |
| LMArena German | 1411 | 1058 |
| LMArena Japanese | 1378 | 1027 |
| LMArena Korean | 1337 | 1008 |
| LMArena Russian | 1405 | 1073 |
| LMArena Spanish | 1431 | 1089 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Qwen1.5-32B: 57.7 (#265)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1116 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Qwen1.5-32B: 34.7 (#246)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1422 | 1146 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Qwen1.5-32B: 34.2 (#271)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1420 | 1137 |
| LMArena Creative Writing | 1401 | 1083 |
| LMArena Multi-Turn | 1408 | 1140 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen1.5-32B?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.5 on the Noometry Index.
Is DeepSeek-V3.1 or Qwen1.5-32B better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Qwen1.5-32B share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen1.5-32B has 21.