Model comparison
DeepSeek-V3.1 vs Qwen1.5-110B
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 33.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Qwen1.5-110B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 38.1.
Side by side
| DeepSeek-V3.1 | Qwen1.5-110B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.2 | 33.6 |
| Released | 2025-08-21 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 39.8 (#140), Qwen1.5-110B: 32.4 (#260)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1417 | 1184 |
| WeirdML | 38.4% | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), Qwen1.5-110B: 21.7 (#192)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1168 |
| ForecastBench | 58 | 57.7 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.1 (#125), Qwen1.5-110B: 31.1 (#199)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1420 | 1185 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), Qwen1.5-110B: 30.7 (#217)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1403 | 1144 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), Qwen1.5-110B: 33.8 (#245)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1400 | 1142 |
| LMArena Chinese | 1470 | 1206 |
| LMArena French | 1447 | 1150 |
| LMArena German | 1412 | 1123 |
| LMArena Japanese | 1374 | 1074 |
| LMArena Korean | 1337 | 1044 |
| LMArena Russian | 1405 | 1118 |
| LMArena Spanish | 1429 | 1141 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 74.1 (#105), Qwen1.5-110B: 60.6 (#247)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1158 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#227), Qwen1.5-110B: 35.0 (#237)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1422 | 1157 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), Qwen1.5-110B: 38.1 (#250)
| Benchmark | DeepSeek-V3.1 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1420 | 1175 |
| LMArena Creative Writing | 1401 | 1148 |
| LMArena Multi-Turn | 1408 | 1160 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen1.5-110B?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 33.6 on the Noometry Index.
Is DeepSeek-V3.1 or Qwen1.5-110B better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 32.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Qwen1.5-110B share?
18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen1.5-110B has 20.