# Gemma 2 2b IT vs Gemma 3 27B

> Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-2b-it-vs-gemma-3-27b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 5 categories and Gemma 3 27B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.7 to 36.6.

## Snapshot

| | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 32.5 | 30.5 |
| Rank | 244 | 277 |
| Context | — | 131K |
| Input $/M | — | $0.08 |
| Output $/M | — | $0.16 |
| Weights | Open | Open |

## Coding

- Gemma 2 2b IT: 31.8 (#268)
- Gemma 3 27B: 22.1 (#329)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Coding | 1112 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| LiveBench Coding | — | 39.9% |

## Agentic & Tool Use

- Gemma 2 2b IT: —
- Gemma 3 27B: 24.9 (#105)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |

## Reasoning

- Gemma 2 2b IT: 20.5 (#219)
- Gemma 3 27B: 16.3 (#297)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1340 |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | — | 51.5% |
| LMCA | — | 12.3% |
| Epoch Capabilities Index | — | 130.04 |
| LiveBench | — | 50% |

## Math

- Gemma 2 2b IT: 30.1 (#212)
- Gemma 3 27B: 24.4 (#261)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1135 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |

## Knowledge

- Gemma 2 2b IT: 29.3 (#229)
- Gemma 3 27B: 25.4 (#256)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Expert | 1096 | 1303 |
| GPQA Diamond | — | 47.7% |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |

## Multimodal

- Gemma 2 2b IT: —
- Gemma 3 27B: 32.0 (#94)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1165 |
| GeoBench | — | 52% |

## Multilingual

- Gemma 2 2b IT: 32.5 (#252)
- Gemma 3 27B: 47.0 (#150)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1121 | 1334 |
| LMArena Chinese | 1132 | 1347 |
| LMArena French | 1156 | 1368 |
| LMArena German | 1114 | 1362 |
| LMArena Japanese | 1083 | 1287 |
| LMArena Korean | 1055 | 1308 |
| LMArena Russian | 1118 | 1349 |
| LMArena Spanish | 1140 | 1348 |

## Instruction Following

- Gemma 2 2b IT: 58.1 (#258)
- Gemma 3 27B: 70.8 (#155)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1321 |
| LiveBench Instruction Following | — | 74.9% |

## Long Context

- Gemma 2 2b IT: 34.2 (#245)
- Gemma 3 27B: 27.6 (#288)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1130 | 1333 |
| Fiction.LiveBench | — | 33.3% |

## Writing & Preference

- Gemma 2 2b IT: 36.6 (#258)
- Gemma 3 27B: 52.7 (#161)

| Benchmark | Gemma 2 2b IT | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1156 | 1358 |
| LMArena Creative Writing | 1147 | 1346 |
| LMArena Multi-Turn | 1118 | 1344 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LiveBench Language | — | 34.6% |

## FAQ

### Is Gemma 2 2b IT better than Gemma 3 27B?

Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 30.5 on the Noometry Index.

### Is Gemma 2 2b IT or Gemma 3 27B better for coding?

Gemma 2 2b IT scores higher on coding benchmarks: 31.8 versus 22.1 in the Noometry coding category.

### How many benchmarks do Gemma 2 2b IT and Gemma 3 27B share?

17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Gemma 3 27B has 43.