# Gemma 2 9B vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 92.2% for Grok 4.20 (Non-Reasoning).
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 25.7 | 48.5 |
| Rank | 334 | 48 |
| Context | — | 1M |
| Input $/M | — | $1.25 |
| Output $/M | — | $2.50 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 9B: 29.0 (#299)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Coding | 1174 | 1458 |
| LMArena WebDev | — | 1374 |
| WeirdML | — | 52.3% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 1,150 |

## Agentic & Tool Use

- Gemma 2 9B: —
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- Gemma 2 9B: 15.3 (#306)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1451 |
| Epoch Capabilities Index | 119.78 | 152.01 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 90.1% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.3 (#312)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 92.2% |
| LMArena Math | 1183 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#300)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 27.5% | 89.3% |
| LMArena Expert | 1147 | 1440 |
| SimpleQA Verified | — | 30.2% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multimodal

- Gemma 2 9B: —
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- Gemma 2 9B: 36.8 (#233)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1188 | 1440 |
| LMArena Chinese | 1185 | 1481 |
| LMArena French | 1189 | 1477 |
| LMArena German | 1186 | 1463 |
| LMArena Japanese | 1144 | 1450 |
| LMArena Korean | 1137 | 1417 |
| LMArena Russian | 1200 | 1457 |
| LMArena Spanish | 1200 | 1442 |

## Instruction Following

- Gemma 2 9B: 57.8 (#264)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1178 | 1420 |
| LiveBench Instruction Following | 52.6% | — |

## Long Context

- Gemma 2 9B: 36.3 (#228)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1197 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- Gemma 2 9B: 32.3 (#276)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | Gemma 2 9B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1207 | 1451 |
| LMArena Creative Writing | 1206 | 1439 |
| EQ-Bench Creative Writing | 841 | 1574 |
| LMArena Multi-Turn | 1193 | 1456 |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 25.7 on the Noometry Index.

### Is Gemma 2 9B or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 29.0 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and Grok 4.20 (Non-Reasoning) share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.