Model comparison
DeepSeek Coder 6.7B vs Qwen-14B
Qwen-14B has enough public results to be ranked (#273); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 1 category and Qwen-14B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.2 to 30.6.
Side by side
| DeepSeek Coder 6.7B | Qwen-14B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.1 | 30.8 |
| Released | 2023-11-02 | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 6.7B leads
DeepSeek Coder 6.7B: 35.2 (#216), Qwen-14B: 30.6 (#283)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1072 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: 18.7 (#255)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 88.88 | 112.8 |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: 28.7 (#224)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| GSM8K | 21.3% | 61.3% |
| LMArena Math | — | 1068 |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: —
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 84.4% |
| MMLU | 36.4% | 66.3% |
| BoolQ | — | 86.2% |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: 27.7 (#270)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: 52.6 (#284)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: 31.3 (#276)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Qwen-14B: 27.8 (#294)
| Benchmark | DeepSeek Coder 6.7B | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Qwen-14B?
Qwen-14B has enough public results to be ranked (#273); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Qwen-14B better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.2 versus 30.6 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Qwen-14B share?
4 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Qwen-14B has 18.