# Gemini 1.5 Flash (May 2024) vs Gemma 3 12B

> Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-flash-vs-gemma-3-12b
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 4 categories and Gemma 3 12B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 1.5 Flash (May 2024) leads 20.8 to 15.2.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Gemini 1.5 Flash (May 2024) and 39.5% for Gemma 3 12B.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 32.9 | 31.8 |
| Rank | 240 | 255 |
| Context | — | 131K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.15 |
| Weights | Proprietary | Open |

## Coding

- Gemini 1.5 Flash (May 2024): 33.9 (#233)
- Gemma 3 12B: 31.2 (#276)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1262 | 1281 |
| SciCode | — | 17.4% |
| WeirdML | 24.9% | — |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |

## Agentic & Tool Use

- Gemini 1.5 Flash (May 2024): 26.3 (#97)
- Gemma 3 12B: 25.3 (#101)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
| BALROG | 14.6% | — |

## Reasoning

- Gemini 1.5 Flash (May 2024): 20.8 (#212)
- Gemma 3 12B: 15.2 (#307)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1309 |
| DTBench | 53.8% | 48.8% |
| Epoch Capabilities Index | 129.37 | 123.49 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMCA | — | 4.5% |
| ForecastBench | 53.9 | — |
| PIQA | 87.5% | — |

## Math

- Gemini 1.5 Flash (May 2024): 20.8 (#274)
- Gemma 3 12B: 21.0 (#273)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 16.7% |
| LMArena Math | 1269 | 1307 |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |

## Knowledge

- Gemini 1.5 Flash (May 2024): 26.2 (#253)
- Gemma 3 12B: 26.5 (#250)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | 47.3% | 39.5% |
| LMArena Expert | 1233 | 1248 |
| MMLU-Pro | 67.8% | — |
| Vectara Hallucination Rate | — | 4.4% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |

## Multimodal

- Gemini 1.5 Flash (May 2024): 35.3 (#76)
- Gemma 3 12B: —

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
| MindCube | — | 46.7% |

## Multilingual

- Gemini 1.5 Flash (May 2024): 43.1 (#184)
- Gemma 3 12B: 45.9 (#160)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1278 | 1318 |
| LMArena German | 1262 | 1370 |
| LMArena Russian | 1288 | 1335 |
| LMArena Chinese | 1295 | — |
| LMArena French | 1257 | — |
| LMArena Japanese | 1252 | — |
| LMArena Korean | 1220 | — |
| LMArena Spanish | 1242 | — |

## Instruction Following

- Gemini 1.5 Flash (May 2024): 67.0 (#199)
- Gemma 3 12B: 68.8 (#179)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1258 | 1299 |
| IFEval | 83.1% | — |

## Long Context

- Gemini 1.5 Flash (May 2024): 39.0 (#182)
- Gemma 3 12B: 40.0 (#157)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1284 | 1317 |

## Writing & Preference

- Gemini 1.5 Flash (May 2024): 48.9 (#190)
- Gemma 3 12B: 47.7 (#205)

| Benchmark | Gemini 1.5 Flash (May 2024) | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1287 | 1334 |
| LMArena Creative Writing | 1285 | 1331 |
| LMArena Multi-Turn | 1253 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |
| WildBench | 79.2% | — |

## FAQ

### Is Gemini 1.5 Flash (May 2024) better than Gemma 3 12B?

Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 31.8 on the Noometry Index.

### Is Gemini 1.5 Flash (May 2024) or Gemma 3 12B better for coding?

Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 33.9 versus 31.2 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Flash (May 2024) and Gemma 3 12B share?

16 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Gemma 3 12B has 24.