Model comparison
DeepSeek Coder 1.3B vs Qwen1.5-7B
Qwen1.5-7B has enough public results to be ranked (#273); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. DeepSeek Coder 1.3B scores higher in 0 categories and Qwen1.5-7B in 1 category, but none of those gaps is larger than the uncertainty.
Side by side
| DeepSeek Coder 1.3B | Qwen1.5-7B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.0 | 31.4 |
| Released | 2023-11-02 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek Coder 1.3B: 31.2 (#287), Qwen1.5-7B: 32.2 (#276)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| BigCodeBench Instruct | 22.8% | — |
| LMArena Coding | — | 1107 |
| BigCodeBench Complete | 29.6% | — |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |
Reasoning Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 20.4 (#240)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | — | 1065 |
| Epoch Capabilities Index | 63.6 | — |
| WinoGrande | 53.3% | — |
Math Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 31.4 (#224)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | — | 1080 |
| GSM8K | 4.4% | — |
Knowledge Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 28.7 (#243)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| MMLU | 25.8% | 62.6% |
| LMArena Expert | — | 1055 |
| ARC (AI2) Challenge | 25.4% | — |
Multilingual Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 28.5 (#271)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | — | 1058 |
| LMArena Chinese | — | 1141 |
| LMArena Russian | — | 1006 |
Instruction Following Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 54.1 (#281)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | — | 1058 |
Long Context Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 33.1 (#266)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | — | 1090 |
Writing & Preference Not comparable
DeepSeek Coder 1.3B: —, Qwen1.5-7B: 29.6 (#293)
| Benchmark | DeepSeek Coder 1.3B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | — | 1083 |
| LMArena Creative Writing | — | 1035 |
| LMArena Multi-Turn | — | 1062 |
Frequently asked questions
Is DeepSeek Coder 1.3B better than Qwen1.5-7B?
Qwen1.5-7B has enough public results to be ranked (#273); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 1.3B or Qwen1.5-7B better for coding?
They score almost the same on coding (31.2 vs 32.2); test both on your own repository before choosing.
How many benchmarks do DeepSeek Coder 1.3B and Qwen1.5-7B share?
1 benchmark has published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and Qwen1.5-7B has 13.