Model comparison
Qwen3.7 Flash vs StarCoder 2 3B
Qwen3.7 Flash has enough public results to be ranked (#152); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- They share 1 benchmark with published results for both.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.7 Flash | StarCoder 2 3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 39.5 | 35.8 |
| Released | 2026-07-15 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.03 | — |
| Output $ / M tokens | $0.13 | — |
| Results tracked | 7 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3.7 Flash: —, StarCoder 2 3B: 32.9
| Benchmark | Qwen3.7 Flash | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Qwen3.7 Flash: 27.3 (#108), StarCoder 2 3B: —
| Benchmark | Qwen3.7 Flash | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 144.62 | 88.01 |
| NYT Connections (extended) | 43.8% | — |
| Chess Puzzles | 23% | — |
| Mystery Game Puzzles | 15% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Qwen3.7 Flash: 37.3 (#100), StarCoder 2 3B: —
| Benchmark | Qwen3.7 Flash | StarCoder 2 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 19.3% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Qwen3.7 Flash: 48.9 (#69), StarCoder 2 3B: —
| Benchmark | Qwen3.7 Flash | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 82.3% | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Frequently asked questions
Is Qwen3.7 Flash better than StarCoder 2 3B?
Qwen3.7 Flash has enough public results to be ranked (#152); StarCoder 2 3B does not yet, so treat this comparison as directional.
How many benchmarks do Qwen3.7 Flash and StarCoder 2 3B share?
1 benchmark has published results for both models. Qwen3.7 Flash has 7 scored results on Noometry and StarCoder 2 3B has 7.