# Gemma 2 2b IT vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.0 to 32.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-2b-it-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.7 to 58.1.
- Gemma 2 2b IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 32.5 | 41.0 |
| Rank | 244 | 130 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 2b IT: 31.8 (#268)
- Grok-3 mini: 40.4 (#126)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1112 | 1380 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |

## Reasoning

- Gemma 2 2b IT: 20.5 (#219)
- Grok-3 mini: 13.8 (#323)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1374 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |

## Math

- Gemma 2 2b IT: 30.1 (#212)
- Grok-3 mini: 40.3 (#78)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Math | 1135 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |

## Knowledge

- Gemma 2 2b IT: 29.3 (#229)
- Grok-3 mini: 46.3 (#75)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1096 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |

## Multilingual

- Gemma 2 2b IT: 32.5 (#252)
- Grok-3 mini: 48.3 (#141)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1121 | 1352 |
| LMArena Chinese | 1132 | 1387 |
| LMArena French | 1156 | 1357 |
| LMArena German | 1114 | 1350 |
| LMArena Japanese | 1083 | 1343 |
| LMArena Korean | 1055 | 1336 |
| LMArena Russian | 1118 | 1352 |
| LMArena Spanish | 1140 | 1379 |

## Instruction Following

- Gemma 2 2b IT: 58.1 (#258)
- Grok-3 mini: 78.7 (#8)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1118 | 1356 |
| IFEval | — | 95.1% |

## Long Context

- Gemma 2 2b IT: 34.2 (#245)
- Grok-3 mini: 41.0 (#142)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1130 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Gemma 2 2b IT: 36.6 (#258)
- Grok-3 mini: 52.7 (#163)

| Benchmark | Gemma 2 2b IT | Grok-3 mini |
|---|---|---|
| LMArena Text | 1156 | 1370 |
| LMArena Creative Writing | 1147 | 1342 |
| LMArena Multi-Turn | 1118 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |

## FAQ

### Is Gemma 2 2b IT better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.0 to 32.5 on the Noometry Index.

### Is Gemma 2 2b IT or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 31.8 in the Noometry coding category.

### How many benchmarks do Gemma 2 2b IT and Grok-3 mini share?

17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Grok-3 mini has 35.