Model comparison
DeepSeek-V3.1 vs Qwen2.5 Plus 1127
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Qwen2.5 Plus 1127 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 49.5.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.2 | 38.1 |
| 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 | 14 |
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), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1417 | 1314 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1299 |
| 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: 36.1 (#125), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1420 | 1298 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1403 | 1289 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1400 | 1265 |
| LMArena Chinese | 1470 | 1314 |
| LMArena German | 1412 | 1231 |
| LMArena Japanese | 1374 | 1207 |
| LMArena Russian | 1405 | 1271 |
| LMArena French | 1447 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1429 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 74.1 (#105), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1275 |
Long Context Qwen2.5 Plus 1127 leads
DeepSeek-V3.1: 36.3 (#227), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1422 | 1292 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | DeepSeek-V3.1 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1420 | 1299 |
| LMArena Creative Writing | 1401 | 1262 |
| LMArena Multi-Turn | 1408 | 1299 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen2.5 Plus 1127?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.
Is DeepSeek-V3.1 or Qwen2.5 Plus 1127 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 37.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen2.5 Plus 1127 has 14.