Model comparison
Qwen Turbo vs StarCoder 2 3B
Qwen Turbo has enough public results to be ranked (#329); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Qwen Turbo | StarCoder 2 3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 26.8 | 35.8 |
| Released | 2024-11-01 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.20 | — |
| Results tracked | 3 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen Turbo: —, StarCoder 2 3B: 32.9
| Benchmark | Qwen Turbo | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Qwen Turbo: —, StarCoder 2 3B: —
| Benchmark | Qwen Turbo | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | — | 88.01 |
| WinoGrande | — | 57.1% |
Math Not comparable
Qwen Turbo: 14.5 (#291), StarCoder 2 3B: —
| Benchmark | Qwen Turbo | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.1% | — |
| MATH Level 5 | 56.2% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Qwen Turbo: 22.2 (#267), StarCoder 2 3B: —
| Benchmark | Qwen Turbo | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 41.8% | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Frequently asked questions
Is Qwen Turbo better than StarCoder 2 3B?
Qwen Turbo has enough public results to be ranked (#329); StarCoder 2 3B does not yet, so treat this comparison as directional.
How many benchmarks do Qwen Turbo and StarCoder 2 3B share?
0 benchmarks have published results for both models. Qwen Turbo has 3 scored results on Noometry and StarCoder 2 3B has 7.