# Gemma 2 27B vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.2 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-27b-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 42.1 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 77.8% for Grok-3 mini.
- Gemma 2 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 29.4 | 41.2 |
| Rank | 312 | 141 |
| Context | 8K | — |
| Input $/M | $0.65 | — |
| Output $/M | $0.65 | — |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 27B: 34.1 (#246)
- Grok-3 mini: 40.8 (#131)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1211 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |

## Reasoning

- Gemma 2 27B: 15.3 (#315)
- Grok-3 mini: 13.6 (#334)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1375 |
| Epoch Capabilities Index | 122.08 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |

## Math

- Gemma 2 27B: 10.7 (#311)
- Grok-3 mini: 42.1 (#85)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 77.8% |
| LMArena Math | 1212 | 1386 |
| MATH Level 5 | 27.9% | 90.9% |
| Omni-MATH | — | 31.8% |
| LiveBench Math | 26.5% | — |
| FrontierMath (Feb 2025 set) | — | 5.9% |

## Knowledge

- Gemma 2 27B: 19.0 (#280)
- Grok-3 mini: 46.4 (#81)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 36.5% | 76.3% |
| Confabulations | 27.1% | 10.8% |
| LMArena Expert | 1172 | 1395 |
| MMLU-Pro | — | 79.9% |
| GPQA (HELM) | — | 67.5% |
| MMLU | 75.7% | — |

## Multilingual

- Gemma 2 27B: 38.6 (#226)
- Grok-3 mini: 48.1 (#145)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1217 | 1352 |
| LMArena Chinese | 1221 | 1387 |
| LMArena French | 1247 | 1357 |
| LMArena German | 1209 | 1349 |
| LMArena Japanese | 1175 | 1342 |
| LMArena Korean | 1174 | 1335 |
| LMArena Russian | 1234 | 1353 |
| LMArena Spanish | 1228 | 1381 |

## Instruction Following

- Gemma 2 27B: 60.5 (#249)
- Grok-3 mini: 78.5 (#9)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1206 | 1357 |
| LiveBench Instruction Following | 58.1% | — |
| IFEval | — | 95.1% |

## Long Context

- Gemma 2 27B: 37.3 (#218)
- Grok-3 mini: 41.0 (#147)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1231 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Gemma 2 27B: 44.2 (#225)
- Grok-3 mini: 52.5 (#169)

| Benchmark | Gemma 2 27B | Grok-3 mini |
|---|---|---|
| LMArena Text | 1231 | 1370 |
| LMArena Creative Writing | 1241 | 1342 |
| LMArena Multi-Turn | 1224 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.4 on the Noometry Index.

### Is Gemma 2 27B or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 34.1 in the Noometry coding category.

### How many benchmarks do Gemma 2 27B and Grok-3 mini share?

22 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Grok-3 mini has 35.