Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen1.5-7B
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Qwen1.5-7B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 50.0 to 29.8.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.0 | 30.8 |
| Released | 2024-09-06 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Qwen1.5-7B: 31.6 (#271)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1310 | 1107 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Qwen1.5-7B: 19.5 (#237)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1066 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Qwen1.5-7B: 29.0 (#222)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1289 | 1080 |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Qwen1.5-7B: 28.2 (#239)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1266 | 1055 |
| MMLU | — | 62.6% |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Qwen1.5-7B: 28.6 (#266)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1273 | 1058 |
| LMArena Chinese | 1317 | 1140 |
| LMArena Russian | 1289 | 1006 |
| LMArena French | 1288 | — |
| 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): 67.7 (#189), Qwen1.5-7B: 54.4 (#276)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1280 | 1058 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Qwen1.5-7B: 33.1 (#261)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1301 | 1090 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Qwen1.5-7B: 29.8 (#288)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1294 | 1084 |
| LMArena Creative Writing | 1285 | 1035 |
| LMArena Multi-Turn | 1297 | 1061 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen1.5-7B?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 30.8 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen1.5-7B better for coding?
They score almost the same on coding (31.3 vs 31.6); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen1.5-7B share?
12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen1.5-7B has 13.