Model comparison
DeepSeek Coder 33B vs Qwen1.5-72B
Qwen1.5-72B has enough public results to be ranked (#285); DeepSeek Coder 33B 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 33B scores higher in 1 category and Qwen1.5-72B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 38.0 to 31.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 51.1% for DeepSeek Coder 33B and 40.3% for Qwen1.5-72B.
Side by side
| DeepSeek Coder 33B | Qwen1.5-72B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 38.9 | 30.8 |
| Released | 2023-11-02 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
DeepSeek Coder 33B: 38.0 (#184), Qwen1.5-72B: 31.9 (#277)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 42% | 33.2% |
| BigCodeBench Complete | 51.1% | 40.3% |
| HumanEval+ | 75% | 59.1% |
| MBPP+ | 70.1% | 61.6% |
| LMArena Coding | — | 1165 |
Reasoning Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 22.2 (#203)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | — | 1148 |
| Epoch Capabilities Index | 96.32 | — |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 33.2 (#205)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 11.5 (#300)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |
Multilingual Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 33.2 (#253)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | — | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 59.3 (#256)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | — | 1141 |
Long Context Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 35.1 (#243)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Qwen1.5-72B: 37.3 (#258)
| Benchmark | DeepSeek Coder 33B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1137 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is DeepSeek Coder 33B better than Qwen1.5-72B?
Qwen1.5-72B has enough public results to be ranked (#285); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Qwen1.5-72B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Qwen1.5-72B share?
4 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Qwen1.5-72B has 22.