Model comparison
Qwen2-72B vs StarCoder 2 3B
Qwen2-72B has enough public results to be ranked (#300); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- They share 3 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 3B leads 33.5 to 29.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 54% for Qwen2-72B and 21.4% for StarCoder 2 3B.
Side by side
| Qwen2-72B | StarCoder 2 3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 30.0 | 36.3 |
| Released | 2024-06-07 | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Qwen2-72B: 29.1 (#310), StarCoder 2 3B: 33.5
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 54% | 21.4% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| LMArena Coding | 1196 | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Not comparable
Qwen2-72B: 23.2 (#181), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 125.28 | 88.76 |
| LMArena Hard Prompts | 1191 | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Qwen2-72B: 30.2 (#236), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1235 | — |
| MATH Level 5 | 39.1% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Qwen2-72B: 21.2 (#275), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| MMLU | 82.4% | 36.6% |
| GPQA Diamond | 40.8% | — |
| LMArena Expert | 1171 | — |
| ARC (AI2) Challenge | — | 34.2% |
Multilingual Not comparable
Qwen2-72B: 35.9 (#244), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1176 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1170 | — |
| LMArena German | 1151 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1083 | — |
| LMArena Russian | 1169 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Not comparable
Qwen2-72B: 61.7 (#241), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1181 | — |
Long Context Not comparable
Qwen2-72B: 36.1 (#235), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1192 | — |
Writing & Preference Not comparable
Qwen2-72B: 40.8 (#241), StarCoder 2 3B: —
| Benchmark | Qwen2-72B | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1203 | — |
| LMArena Creative Writing | 1181 | — |
| LMArena Multi-Turn | 1196 | — |
Frequently asked questions
Is Qwen2-72B better than StarCoder 2 3B?
Qwen2-72B has enough public results to be ranked (#300); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Qwen2-72B or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 33.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and StarCoder 2 3B share?
3 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and StarCoder 2 3B has 7.