# Gemini 1.5 Flash 8B vs Gemma 3 12B

> Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-flash-8b-vs-gemma-3-12b
- Last updated: 2026-10-12
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemini 1.5 Flash 8B scores higher in 2 categories and Gemma 3 12B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 16.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.6% for Gemini 1.5 Flash 8B and 16.7% for Gemma 3 12B.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 29.9 | 32.1 |
| Rank | 301 | 262 |
| Context | — | 131K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.15 |
| Weights | Proprietary | Open |

## Coding

- Gemini 1.5 Flash 8B: 35.5 (#225)
- Gemma 3 12B: 31.7 (#280)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1218 | 1281 |
| SciCode | — | 17.4% |

## Agentic & Tool Use

- Gemini 1.5 Flash 8B: —
- Gemma 3 12B: 25.5 (#108)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |

## Reasoning

- Gemini 1.5 Flash 8B: 20.0 (#244)
- Gemma 3 12B: 15.7 (#313)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1209 | 1309 |
| DTBench | 50% | 48.8% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMCA | — | 4.5% |
| Epoch Capabilities Index | — | 123.5 |

## Math

- Gemini 1.5 Flash 8B: 14.2 (#302)
- Gemma 3 12B: 22.3 (#279)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.6% | 16.7% |
| LMArena Math | 1207 | 1307 |

## Knowledge

- Gemini 1.5 Flash 8B: 16.0 (#289)
- Gemma 3 12B: 26.5 (#257)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | 33% | 39.5% |
| LMArena Expert | 1185 | 1248 |
| Vectara Hallucination Rate | — | 4.4% |

## Multimodal

- Gemini 1.5 Flash 8B: 28.2 (#115)
- Gemma 3 12B: —

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1044 | — |
| MindCube | — | 46.7% |

## Multilingual

- Gemini 1.5 Flash 8B: 38.5 (#229)
- Gemma 3 12B: 45.7 (#165)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1215 | 1318 |
| LMArena German | 1206 | 1370 |
| LMArena Russian | 1236 | 1335 |
| LMArena Chinese | 1231 | — |
| LMArena French | 1234 | — |
| LMArena Japanese | 1150 | — |
| LMArena Korean | 1140 | — |
| LMArena Spanish | 1212 | — |

## Instruction Following

- Gemini 1.5 Flash 8B: 62.8 (#236)
- Gemma 3 12B: 68.6 (#186)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1299 |

## Long Context

- Gemini 1.5 Flash 8B: 37.0 (#225)
- Gemma 3 12B: 40.0 (#162)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1219 | 1317 |

## Writing & Preference

- Gemini 1.5 Flash 8B: 42.8 (#232)
- Gemma 3 12B: 47.5 (#209)

| Benchmark | Gemini 1.5 Flash 8B | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1226 | 1334 |
| LMArena Creative Writing | 1218 | 1331 |
| LMArena Multi-Turn | 1185 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |

## FAQ

### Is Gemini 1.5 Flash 8B better than Gemma 3 12B?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.9 on the Noometry Index.

### Is Gemini 1.5 Flash 8B or Gemma 3 12B better for coding?

Gemini 1.5 Flash 8B scores higher on coding benchmarks: 35.5 versus 31.7 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Flash 8B and Gemma 3 12B share?

15 benchmarks have published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and Gemma 3 12B has 24.