# Gemini 2.5 Flash-Lite vs Gemma 3 12B

> Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 31.8 on the Noometry Index. Gemma 3 12B costs 2.3× less per token, which makes it the better buy when Gemini 2.5 Flash-Lite's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-gemma-3-12b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 8 categories and Gemma 3 12B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash-Lite leads 35.5 to 21.0.
- The biggest single-benchmark swing is DTBench: 62.8% for Gemini 2.5 Flash-Lite and 48.8% for Gemma 3 12B.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.10 / $0.40 for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 131K.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 36.4 | 31.8 |
| Rank | 208 | 255 |
| Context | 1.05M | 131K |
| Input $/M | $0.10 | $0.05 |
| Output $/M | $0.40 | $0.15 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.0 (#167)
- Gemma 3 12B: 31.2 (#276)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1373 | 1281 |
| SciCode | — | 17.4% |
| WeirdML | 35.2% | — |
| ALE-Bench | 325.9 | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 27.8 (#89)
- Gemma 3 12B: 25.3 (#101)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 30.4% |

## Reasoning

- Gemini 2.5 Flash-Lite: 21.5 (#196)
- Gemma 3 12B: 15.2 (#307)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1309 |
| DTBench | 62.8% | 48.8% |
| LMCA | 18.1% | 4.5% |
| Epoch Capabilities Index | 133.93 | 123.49 |
| Kagi LLM Benchmark | 40.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |

## Math

- Gemini 2.5 Flash-Lite: 35.5 (#144)
- Gemma 3 12B: 21.0 (#273)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Math | 1373 | 1307 |
| OTIS Mock AIME 2024-2025 | — | 16.7% |
| Omni-MATH | 48% | — |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.1 (#206)
- Gemma 3 12B: 26.5 (#250)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 4.4% |
| LMArena Expert | 1373 | 1248 |
| GPQA Diamond | — | 39.5% |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 28.6 (#109)
- Gemma 3 12B: —

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
| MindCube | — | 46.7% |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.5 (#129)
- Gemma 3 12B: 45.9 (#160)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1369 | 1318 |
| LMArena German | 1390 | 1370 |
| LMArena Russian | 1373 | 1335 |
| LMArena Chinese | 1404 | — |
| LMArena French | 1388 | — |
| LMArena Japanese | 1359 | — |
| LMArena Korean | 1358 | — |
| LMArena Spanish | 1396 | — |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.2 (#163)
- Gemma 3 12B: 68.8 (#179)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1366 | 1299 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#257)
- Gemma 3 12B: 40.0 (#157)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1373 | 1317 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 57.0 (#130)
- Gemma 3 12B: 47.7 (#205)

| Benchmark | Gemini 2.5 Flash-Lite | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1379 | 1334 |
| LMArena Creative Writing | 1366 | 1331 |
| LMArena Multi-Turn | 1367 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Gemma 3 12B?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 31.8 on the Noometry Index. Gemma 3 12B costs 2.3× less per token, which makes it the better buy when Gemini 2.5 Flash-Lite's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash-Lite or Gemma 3 12B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Gemini 2.5 Flash-Lite lists at $0.10 and $0.40.

### Is Gemini 2.5 Flash-Lite or Gemma 3 12B better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash-Lite does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 2.5 Flash-Lite and Gemma 3 12B share?

17 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Gemma 3 12B has 24.