Model comparison
Qwen2.5-Coder-32B vs StarCoder 2 15B
Qwen2.5-Coder-32B has enough public results to be ranked (#245); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 7 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- They share 7 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.6 to 22.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 58% for Qwen2.5-Coder-32B and 38.4% for StarCoder 2 15B.
Side by side
| Qwen2.5-Coder-32B | StarCoder 2 15B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 33.4 | 38.1 |
| Released | 2024-09-18 | 2024-02-20 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 29K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 31 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
Qwen2.5-Coder-32B: 22.6 (#333), StarCoder 2 15B: 36.6
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 58% | 38.4% |
| HumanEval+ | 87.2% | 37.8% |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| LMArena Coding | 1276 | — |
| MBPP+ | 77% | — |
Reasoning Not comparable
Qwen2.5-Coder-32B: 21.2 (#225), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 119.49 | 105 |
| WinoGrande | 80.8% | 64.3% |
| LiveBench Reasoning | 42.1% | — |
| LMArena Hard Prompts | 1251 | — |
| LiveBench Data Analysis | 49.9% | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
Math Not comparable
Qwen2.5-Coder-32B: 33.3 (#204), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| GSM8K | 93% | 57.7% |
| LiveBench Math | 46.6% | — |
| LMArena Math | 1251 | — |
Knowledge Not comparable
Qwen2.5-Coder-32B: 33.4 (#203), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| ARC (AI2) Challenge | 70.5% | 47.2% |
| MMLU | 79.1% | 64.1% |
| LMArena Expert | 1221 | — |
Multilingual Not comparable
Qwen2.5-Coder-32B: 37.8 (#235), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1222 | — |
| LMArena Russian | 1228 | — |
Instruction Following Not comparable
Qwen2.5-Coder-32B: 61.4 (#245), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| LiveBench Instruction Following | 58.7% | — |
| LMArena Instruction Following | 1223 | — |
Long Context Not comparable
Qwen2.5-Coder-32B: 38.0 (#208), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1251 | — |
Writing & Preference Not comparable
Qwen2.5-Coder-32B: 41.6 (#240), StarCoder 2 15B: —
| Benchmark | Qwen2.5-Coder-32B | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1230 | — |
| LMArena Creative Writing | 1174 | — |
| LMArena Multi-Turn | 1222 | — |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than StarCoder 2 15B?
Qwen2.5-Coder-32B has enough public results to be ranked (#245); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Qwen2.5-Coder-32B or StarCoder 2 15B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.6 versus 22.6 in the Noometry coding category.
How many benchmarks do Qwen2.5-Coder-32B and StarCoder 2 15B share?
7 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and StarCoder 2 15B has 7.