Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen2.5-Coder-32B
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2.5 (Sep 2024) leads 31.7 to 22.6.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 33.4 |
| Released | 2024-09-06 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 22 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| Aider Polyglot | 17.8% | 16.4% |
| BigCodeBench Instruct | 48.6% | 49% |
| LMArena Coding | 1309 | 1276 |
| BigCodeBench Complete | 53.2% | 58% |
| HumanEval+ | 83.5% | 87.2% |
| MBPP+ | 74.1% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| LiveBench Coding | — | 56.9% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1288 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1266 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1273 | 1205 |
| LMArena Chinese | 1318 | 1222 |
| LMArena Russian | 1289 | 1228 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1280 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1301 | 1251 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1294 | 1230 |
| LMArena Creative Writing | 1285 | 1174 |
| LMArena Multi-Turn | 1297 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen2.5-Coder-32B?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.4 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen2.5-Coder-32B better for coding?
DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 22.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen2.5-Coder-32B share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen2.5-Coder-32B has 31.