# Gemma 3 12B vs Nova 2.0 Pro Preview

> Nova 2.0 Pro Preview is the stronger model overall, scoring 32.8 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-nova-2-0-pro-preview
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Nova 2.0 Pro Preview in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nova 2.0 Pro Preview leads 40.2 to 31.2.
- The biggest single-benchmark swing is SciCode: 17.4% for Gemma 3 12B and 42.7% for Nova 2.0 Pro Preview.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| Provider | Google | Amazon |
| Noometry Index | 31.8 | 32.8 |
| Rank | 255 | 241 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 12B: 31.2 (#276)
- Nova 2.0 Pro Preview: 40.2 (#130)

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| SciCode | 17.4% | 42.7% |
| LMArena Coding | 1281 | — |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- Nova 2.0 Pro Preview: 21.9 (#127)

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
| GDP.pdf | — | 2% |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- Nova 2.0 Pro Preview: 21.7 (#189)

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| CritPt | 0% | 0% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1309 | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |

## Math

- Gemma 3 12B: 21.0 (#273)
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| LMArena Math | 1307 | — |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |

## Multimodal

- Gemma 3 12B: —
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1299 | — |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1317 | — |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- Nova 2.0 Pro Preview: —

| Benchmark | Gemma 3 12B | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Text | 1334 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1126 | — |
| LMArena Multi-Turn | 1334 | — |

## FAQ

### Is Gemma 3 12B better than Nova 2.0 Pro Preview?

Nova 2.0 Pro Preview is the stronger model overall, scoring 32.8 to 31.8 on the Noometry Index.

### Is Gemma 3 12B or Nova 2.0 Pro Preview better for coding?

Nova 2.0 Pro Preview scores higher on coding benchmarks: 40.2 versus 31.2 in the Noometry coding category.

### How many benchmarks do Gemma 3 12B and Nova 2.0 Pro Preview share?

2 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Nova 2.0 Pro Preview has 3.