Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen Plus
DeepSeek-V2.5 (Sep 2024) and Qwen Plus score almost the same on the Noometry Index (37.6 vs 37.1), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 2 categories and Qwen Plus in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 35.9 to 23.3.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 37.1 |
| Released | 2024-09-06 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 22 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Qwen Plus: 38.9 (#167)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Coding | 1309 | 1328 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Qwen Plus leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Qwen Plus: 28.4 (#107)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1317 |
| Kagi LLM Benchmark | — | 63.3% |
| DTBench | — | 81.1% |
| LMCA | — | 24% |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Qwen Plus: 23.3 (#271)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Math | 1288 | 1326 |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Qwen Plus: 27.4 (#251)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Expert | 1266 | 1328 |
| GPQA Diamond | — | 48.1% |
Multilingual Qwen Plus leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Qwen Plus: 45.1 (#175)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1273 | 1310 |
| LMArena Chinese | 1318 | 1347 |
| LMArena Japanese | 1228 | 1251 |
| LMArena Russian | 1289 | 1323 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Qwen Plus leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Qwen Plus: 68.8 (#181)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1280 | 1303 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Qwen Plus: 40.3 (#158)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1301 | 1324 |
Writing & Preference Qwen Plus leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Qwen Plus: 52.2 (#176)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen Plus |
|---|---|---|
| LMArena Text | 1294 | 1326 |
| LMArena Creative Writing | 1285 | 1293 |
| LMArena Multi-Turn | 1297 | 1336 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen Plus?
DeepSeek-V2.5 (Sep 2024) and Qwen Plus score almost the same on the Noometry Index (37.6 vs 37.1), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen Plus share?
13 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen Plus has 20.