Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen1.5-110B
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 33.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Qwen1.5-110B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 50.0 to 38.1.
- The biggest single-benchmark swing is BigCodeBench Instruct: 48.6% for DeepSeek-V2.5 (Sep 2024) and 35% for Qwen1.5-110B.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.0 | 33.6 |
| Released | 2024-09-06 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Qwen1.5-110B: 32.4 (#260)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| BigCodeBench Instruct | 48.6% | 35% |
| LMArena Coding | 1310 | 1184 |
| BigCodeBench Complete | 53.2% | 44.4% |
| Aider Polyglot | 17.8% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Qwen1.5-110B: 21.7 (#192)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1168 |
| ForecastBench | — | 57.7 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Qwen1.5-110B: 31.1 (#199)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1289 | 1185 |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Qwen1.5-110B: 30.7 (#217)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1266 | 1144 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Qwen1.5-110B: 33.8 (#245)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1273 | 1142 |
| LMArena Chinese | 1317 | 1206 |
| LMArena French | 1288 | 1150 |
| LMArena German | 1258 | 1123 |
| LMArena Japanese | 1228 | 1074 |
| LMArena Korean | 1209 | 1044 |
| LMArena Russian | 1289 | 1118 |
| LMArena Spanish | 1248 | 1141 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Qwen1.5-110B: 60.6 (#247)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1280 | 1158 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Qwen1.5-110B: 35.0 (#237)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1301 | 1157 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Qwen1.5-110B: 38.1 (#250)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1294 | 1175 |
| LMArena Creative Writing | 1285 | 1148 |
| LMArena Multi-Turn | 1297 | 1160 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen1.5-110B?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 33.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 32.4 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen1.5-110B share?
19 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen1.5-110B has 20.