Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 4 categories and Qwen2.5 Plus 1127 in 4 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5 Plus 1127 leads 37.9 to 31.3.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.0 | 38.1 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1310 | 1314 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1299 |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1289 | 1298 |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1266 | 1289 |
Multilingual Too close to call
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1273 | 1265 |
| LMArena Chinese | 1317 | 1314 |
| LMArena German | 1258 | 1231 |
| LMArena Japanese | 1228 | 1207 |
| LMArena Russian | 1289 | 1271 |
| LMArena French | 1288 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Too close to call
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1275 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1301 | 1292 |
Writing & Preference Too close to call
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1294 | 1299 |
| LMArena Creative Writing | 1285 | 1262 |
| LMArena Multi-Turn | 1297 | 1299 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 37.9 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen2.5 Plus 1127 has 14.