Model comparison
Gemma 3 1B vs StarCoder 2 15B
Gemma 3 1B has enough public results to be ranked (#353); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
NVIDIASide by side
| Gemma 3 1B | StarCoder 2 15B | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 21.1 | 38.1 |
| Released | 2025-03-12 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 4 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 1B: —, StarCoder 2 15B: 36.6
| Benchmark | Gemma 3 1B | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |
Agentic & Tool Use Not comparable
Gemma 3 1B: 13.7 (#152), StarCoder 2 15B: —
| Benchmark | Gemma 3 1B | StarCoder 2 15B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |
Reasoning Not comparable
Gemma 3 1B: 19.2 (#264), StarCoder 2 15B: —
| Benchmark | Gemma 3 1B | StarCoder 2 15B |
|---|---|---|
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | — | 105 |
| WinoGrande | — | 64.3% |
Math Not comparable
Gemma 3 1B: 10.2 (#316), StarCoder 2 15B: —
| Benchmark | Gemma 3 1B | StarCoder 2 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Gemma 3 1B: 7.0 (#314), StarCoder 2 15B: —
| Benchmark | Gemma 3 1B | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 19.9% | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Frequently asked questions
Is Gemma 3 1B better than StarCoder 2 15B?
Gemma 3 1B has enough public results to be ranked (#353); StarCoder 2 15B does not yet, so treat this comparison as directional.
How many benchmarks do Gemma 3 1B and StarCoder 2 15B share?
0 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and StarCoder 2 15B has 7.