# Gemma 3 12B vs StarCoder 2 15B

> Gemma 3 12B has enough public results to be ranked (#262); StarCoder 2 15B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-starcoder-2-15b
- Last updated: 2026-10-12
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Gemma 3 12B scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.6 to 31.7.

## Snapshot

| | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| Provider | Google | NVIDIA |
| Noometry Index | 32.1 | 38.1 |
| Rank | 262 | — |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- StarCoder 2 15B: 36.6

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| SciCode | 17.4% | — |
| LMArena Coding | 1281 | — |
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 123.5 | 105 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1309 | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| WinoGrande | — | 64.3% |

## Math

- Gemma 3 12B: 22.3 (#279)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| LMArena Math | 1307 | — |
| GSM8K | — | 57.7% |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |

## Multimodal

- Gemma 3 12B: —
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1299 | — |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1317 | — |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- StarCoder 2 15B: —

| Benchmark | Gemma 3 12B | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1334 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1126 | — |
| LMArena Multi-Turn | 1334 | — |

## FAQ

### Is Gemma 3 12B better than StarCoder 2 15B?

Gemma 3 12B has enough public results to be ranked (#262); StarCoder 2 15B does not yet, so treat this comparison as directional.

### Is Gemma 3 12B or StarCoder 2 15B better for coding?

StarCoder 2 15B scores higher on coding benchmarks: 36.6 versus 31.7 in the Noometry coding category.

### How many benchmarks do Gemma 3 12B and StarCoder 2 15B share?

1 benchmark has published results for both models. Gemma 3 12B has 24 scored results on Noometry and StarCoder 2 15B has 7.
