Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 37.6 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 1 category and Qwen2.5-Max in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5-Max leads 41.8 to 31.7.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 40.7 |
| Released | 2024-09-06 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Qwen2.5-Max: 41.8 (#117)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1309 | 1359 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| LiveBench Coding | — | 64.4% |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Qwen2.5-Max: 25.6 (#147)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1360 |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.53 |
| LiveBench | — | 62.3% |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Qwen2.5-Max: 36.9 (#162)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1288 | 1369 |
| LiveBench Math | — | 58.4% |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Qwen2.5-Max: 35.3 (#186)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1266 | 1337 |
| Confabulations | — | 21.8% |
Multilingual Qwen2.5-Max leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Qwen2.5-Max: 48.1 (#146)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1273 | 1352 |
| LMArena Chinese | 1318 | 1382 |
| LMArena French | 1289 | 1396 |
| LMArena German | 1258 | 1350 |
| LMArena Japanese | 1228 | 1300 |
| LMArena Korean | 1209 | 1304 |
| LMArena Russian | 1289 | 1353 |
| LMArena Spanish | 1248 | 1377 |
Instruction Following Qwen2.5-Max leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Qwen2.5-Max: 71.3 (#152)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1280 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Qwen2.5-Max: 41.4 (#142)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1301 | 1358 |
Writing & Preference Qwen2.5-Max leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Qwen2.5-Max: 55.4 (#146)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1294 | 1367 |
| LMArena Creative Writing | 1285 | 1339 |
| LMArena Multi-Turn | 1297 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen2.5-Max share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen2.5-Max has 27.