Model comparison
Qwen3 8B vs StarCoder 2 3B
Qwen3 8B has enough public results to be ranked (#237); 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. Qwen3 8B scores higher in 1 category and StarCoder 2 3B in 0 categories, but none of those gaps is larger than the uncertainty.
Side by side
| Qwen3 8B | StarCoder 2 3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 33.3 | 35.8 |
| Released | 2025-04 | 2024-02-22 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.18 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 11 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen3 8B: 33.4 (#245), StarCoder 2 3B: 32.9
| Benchmark | Qwen3 8B | StarCoder 2 3B |
|---|---|---|
| SciCode | 22.6% | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Qwen3 8B: 29.9 (#71), StarCoder 2 3B: —
| Benchmark | Qwen3 8B | StarCoder 2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 42.6% | — |
Reasoning Not comparable
Qwen3 8B: 16.1 (#299), StarCoder 2 3B: —
| Benchmark | Qwen3 8B | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 136.17 | 88.01 |
| CritPt | 0% | — |
| Chess Puzzles | 5% | — |
| DTBench | 59.7% | — |
| LMCA | 8.8% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Qwen3 8B: 33.3 (#176), StarCoder 2 3B: —
| Benchmark | Qwen3 8B | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 56.1% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Qwen3 8B: 36.1 (#164), StarCoder 2 3B: —
| Benchmark | Qwen3 8B | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 56.8% | — |
| Vectara Hallucination Rate | 4.8% | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Long Context Not comparable
Qwen3 8B: 37.8 (#205), StarCoder 2 3B: —
| Benchmark | Qwen3 8B | StarCoder 2 3B |
|---|---|---|
| Fiction.LiveBench | 62.1% | — |
Frequently asked questions
Is Qwen3 8B better than StarCoder 2 3B?
Qwen3 8B has enough public results to be ranked (#237); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Qwen3 8B or StarCoder 2 3B better for coding?
They score almost the same on coding (33.4 vs 32.9); test both on your own repository before choosing.
How many benchmarks do Qwen3 8B and StarCoder 2 3B share?
1 benchmark has published results for both models. Qwen3 8B has 11 scored results on Noometry and StarCoder 2 3B has 7.