# Gemma 3 12B vs Gemma 4 31B IT

> Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 31.8 on the Noometry Index. Gemma 3 12B costs 2.0× less per token, which makes it the better buy when Gemma 4 31B IT's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-gemma-4-31b-it
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 73.3% for Gemma 4 31B IT.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.09 / $0.34 for Gemma 4 31B IT.
- Gemma 4 31B IT accepts more context: 262K tokens versus 131K.

## Snapshot

| | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 31.8 | 43.2 |
| Rank | 255 | 85 |
| Context | 131K | 262K |
| Input $/M | $0.05 | $0.09 |
| Output $/M | $0.15 | $0.34 |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.2 (#276)
- Gemma 4 31B IT: 41.9 (#98)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| SciCode | 17.4% | 43.4% |
| LMArena Coding | 1281 | 1459 |
| LMArena WebDev | — | 1364 |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 925.5 |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- Gemma 4 31B IT: —

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- Gemma 4 31B IT: 26.4 (#119)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| CritPt | 0% | 1.4% |
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1309 | 1448 |
| DTBench | 48.8% | 82.7% |
| LMCA | 4.5% | 39.3% |
| Epoch Capabilities Index | 123.49 | 142.74 |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| Thematic Generalization | — | 53% |
| Surface Evolver Bench | — | 30.6% |

## Math

- Gemma 3 12B: 21.0 (#273)
- Gemma 4 31B IT: 41.3 (#72)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 73.3% |
| LMArena Math | 1307 | 1464 |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- Gemma 4 31B IT: 37.9 (#141)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 39.5% | 75.8% |
| Vectara Hallucination Rate | 4.4% | 7.4% |
| LMArena Expert | 1248 | 1465 |
| SimpleQA Verified | — | 10.4% |

## Multimodal

- Gemma 3 12B: —
- Gemma 4 31B IT: 41.0 (#32)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| LMArena Document | — | 1425 |
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- Gemma 4 31B IT: 54.0 (#52)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1318 | 1431 |
| LMArena Russian | 1335 | 1462 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1436 |
| LMArena German | 1370 | — |
| LMArena Spanish | — | 1443 |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- Gemma 4 31B IT: 75.6 (#58)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1299 | 1433 |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- Gemma 4 31B IT: 44.2 (#67)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1317 | 1446 |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- Gemma 4 31B IT: 60.7 (#92)

| Benchmark | Gemma 3 12B | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1334 | 1443 |
| LMArena Creative Writing | 1331 | 1416 |
| EQ-Bench Creative Writing | 1126 | 1368 |
| LMArena Multi-Turn | 1334 | 1452 |
| EQ-Bench 4 | — | 1120 |

## FAQ

### Is Gemma 3 12B better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 31.8 on the Noometry Index. Gemma 3 12B costs 2.0× less per token, which makes it the better buy when Gemma 4 31B IT's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 12B or Gemma 4 31B IT?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Gemma 4 31B IT lists at $0.09 and $0.34.

### Is Gemma 3 12B or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 131K.

### How many benchmarks do Gemma 3 12B and Gemma 4 31B IT share?

21 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Gemma 4 31B IT has 35.