# Gemma 2 9B vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.0 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.3 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 77.8% for Grok-3 mini.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 25.7 | 41.0 |
| Rank | 334 | 130 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 9B: 29.0 (#299)
- Grok-3 mini: 40.4 (#126)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1174 | 1380 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |

## Reasoning

- Gemma 2 9B: 15.3 (#306)
- Grok-3 mini: 13.8 (#323)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1374 |
| Epoch Capabilities Index | 119.78 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.3 (#312)
- Grok-3 mini: 40.3 (#78)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 77.8% |
| LMArena Math | 1183 | 1386 |
| MATH Level 5 | 21% | 90.9% |
| Omni-MATH | — | 31.8% |
| LiveBench Math | 19.8% | — |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#300)
- Grok-3 mini: 46.3 (#75)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 27.5% | 76.3% |
| LMArena Expert | 1147 | 1395 |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multilingual

- Gemma 2 9B: 36.8 (#233)
- Grok-3 mini: 48.3 (#141)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1188 | 1352 |
| LMArena Chinese | 1185 | 1387 |
| LMArena French | 1189 | 1357 |
| LMArena German | 1186 | 1350 |
| LMArena Japanese | 1144 | 1343 |
| LMArena Korean | 1137 | 1336 |
| LMArena Russian | 1200 | 1352 |
| LMArena Spanish | 1200 | 1379 |

## Instruction Following

- Gemma 2 9B: 57.8 (#264)
- Grok-3 mini: 78.7 (#8)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1178 | 1356 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 95.1% |

## Long Context

- Gemma 2 9B: 36.3 (#228)
- Grok-3 mini: 41.0 (#142)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1197 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Gemma 2 9B: 32.3 (#276)
- Grok-3 mini: 52.7 (#163)

| Benchmark | Gemma 2 9B | Grok-3 mini |
|---|---|---|
| LMArena Text | 1207 | 1370 |
| LMArena Creative Writing | 1206 | 1342 |
| LMArena Multi-Turn | 1193 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 841 | — |
| WildBench | — | 65.1% |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.0 to 25.7 on the Noometry Index.

### Is Gemma 2 9B or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 29.0 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and Grok-3 mini share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Grok-3 mini has 35.