# Gemma 4 12B Benchmark Scores & Performance

> Gemma 4 12B by Google scores 46.64/100 overall, ranking #154 out of 411 AI models.

Canonical page: https://benchlm.ai/models/gemma-4-12b

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Google |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | 46.64/100 |
| Overall Rank | #154 of 411 |

## Family & Coverage

- Family: Gemma 4
- Variant: 12b
- Benchmarks covered: 27 of 422
- Sibling models: [Gemma 4 31B](/models/gemma-4-31b), [Gemma 4 26B A4B](/models/gemma-4-26b-a4b), [Gemma 4 E4B](/models/gemma-4-e4b), [Gemma 4 E2B](/models/gemma-4-e2b)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 36.3% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 7.3% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 647 |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 72.0% |
| [AA-SciCode](/benchmarks/aascicode) | 38.2% |
| [AA Coding Index](/benchmarks/aacodingindex) | 31.0% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [MMMU-Pro](/benchmarks/mmmu-pro) | 69.1% |
| [MathVision](/benchmarks/mathvision) | 79.7% |
| [MedXpertQA (MM)](/benchmarks/medxpertqamm) | 48.7% |
| [AA-MMMU-Pro](/benchmarks/aammmupro) | 69.7% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [BBH](/benchmarks/bbh) | 53% |
| [MRCRv2](/benchmarks/mrcrv2) | 43.4% |
| [AA-LCR](/benchmarks/lcr) | 61.7% |
| [CritPt](/benchmarks/critpt) | 0.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [GPQA](/benchmarks/gpqa) | 78.8% |
| [GPQA-D](/benchmarks/gpqa-diamond) | 78.8% |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 77.2% |
| [HLE w/o tools](/benchmarks/hlenotools) | 5.2% |
| [MMMLU](/benchmarks/mmmlu) | 83.4% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 22.2% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 75.3% |
| [AA-HLE](/benchmarks/aahle) | 15.7% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -52.7% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 15.6% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 81.0% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 73.5% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AIME26](/benchmarks/aime2026) | 77.5% |

## Other Google Models

- [Gemini 3.8 Flash](/models/gemini-3-8-flash) - Score: 78.41
- [Gemini 3.7 Flash](/models/gemini-3-7-flash) - Score: 70.2
- [Gemini 3.6 Flash](/models/gemini-3-6-flash) - Score: 70.1
- [Gemini 3.5 Flash](/models/gemini-3-5-flash) - Score: 70
- [Gemini 3.1 Pro](/models/gemini-3-1-pro) - Score: 69.82
- [Gemini 3 Pro](/models/gemini-3-pro) - Score: 67.23
- [Gemini 3 Flash](/models/gemini-3-flash) - Score: 62.96
- [Gemini 3 Pro Deep Think](/models/gemini-3-pro-deep-think) - Score: 60.67
- [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) - Score: 60.5
- [Gemma 4 31B](/models/gemma-4-31b) - Score: 58.69
- [Gemini 2.5 Pro](/models/gemini-2-5-pro) - Score: 57.98
- [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) - Score: 56.66
- [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) - Score: 56.13
- [Gemini 2.5 Flash](/models/gemini-2-5-flash) - Score: 51.68
- [Gemma 4 E4B](/models/gemma-4-e4b) - Score: 42.92
- [Gemma 4 E2B](/models/gemma-4-e2b) - Score: 41.94
- [Gemma 3 27B](/models/gemma-3-27b) - Score: 38.2
- [Gemini 1.5 Pro](/models/gemini-1-5-pro) - Score: 34.88
- [Gemini 1.0 Pro](/models/gemini-1-0-pro) - Score: 15.31
- [Gemini 3.8 Flash Cyber](/models/gemini-3-8-flash-cyber) - Score: not computed
- [Gemini 3.5 Flash Cyber](/models/gemini-3-5-flash-cyber) - Score: not computed
- [Gemini 3.1 Flash TTS Preview](/models/gemini-3-1-flash-tts-preview) - Score: not computed
- [Gemini 2.5 Flash Native Audio Preview (12-2025)](/models/gemini-2-5-flash-native-audio-preview-12-2025) - Score: not computed
- [Gemini 2.5 Flash TTS Preview](/models/gemini-2-5-flash-tts-preview) - Score: not computed
- [Gemini 2.5 Pro TTS Preview](/models/gemini-2-5-pro-tts-preview) - Score: not computed
- [Gemini 3.1 Flash Live Preview](/models/gemini-3-1-flash-live-preview) - Score: not computed