# Gemma 2 9B vs Llama 4 Maverick

> Llama 4 Maverick is the stronger model overall, scoring 30.9 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-llama-4-maverick
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemma 2 9B scores higher in 3 categories and Llama 4 Maverick in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Maverick leads 33.4 to 9.7.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 73% for Llama 4 Maverick.

## Snapshot

| | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 25.9 | 30.9 |
| Rank | 341 | 282 |
| Context | — | 128K |
| Input $/M | — | $0.19 |
| Output $/M | — | $0.65 |
| Weights | Open | Open |

## Coding

- Gemma 2 9B: 29.4 (#304)
- Llama 4 Maverick: 26.6 (#324)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 49.7% |
| LMArena Coding | 1173 | 1302 |
| BigCodeBench Complete | 40.6% | 61.4% |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| LiveBench Coding | 22.5% | — |
| ALE-Bench | — | 172.97 |

## Agentic & Tool Use

- Gemma 2 9B: —
- Llama 4 Maverick: 28.2 (#91)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- Llama 4 Maverick: 10.1 (#342)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1281 |
| Epoch Capabilities Index | 119.83 | 132.2 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 61.9% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 15.9% |
| ForecastBench | — | 57.5 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- Llama 4 Maverick: 26.0 (#262)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 20.6% |
| LMArena Math | 1183 | 1299 |
| MATH Level 5 | 21% | 73% |
| Omni-MATH | — | 42.2% |
| LiveBench Math | 19.8% | — |
| FrontierMath (Feb 2025 set) | — | 0.7% |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- Llama 4 Maverick: 33.4 (#204)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 27.5% | 67% |
| LMArena Expert | 1147 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multimodal

- Gemma 2 9B: —
- Llama 4 Maverick: 31.6 (#105)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- Llama 4 Maverick: 42.2 (#195)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1188 | 1269 |
| LMArena Chinese | 1185 | 1277 |
| LMArena French | 1190 | 1259 |
| LMArena German | 1186 | 1291 |
| LMArena Japanese | 1144 | 1207 |
| LMArena Korean | 1137 | 1203 |
| LMArena Russian | 1200 | 1286 |
| LMArena Spanish | 1200 | 1293 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- Llama 4 Maverick: 71.7 (#146)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1178 | 1267 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 90.8% |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- Llama 4 Maverick: 31.4 (#279)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1197 | 1280 |
| Fiction.LiveBench | — | 46.2% |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- Llama 4 Maverick: 38.8 (#252)

| Benchmark | Gemma 2 9B | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1207 | 1287 |
| LMArena Creative Writing | 1206 | 1267 |
| EQ-Bench Creative Writing | 841 | 860 |
| LMArena Multi-Turn | 1193 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than Llama 4 Maverick?

Llama 4 Maverick is the stronger model overall, scoring 30.9 to 25.9 on the Noometry Index.

### Is Gemma 2 9B or Llama 4 Maverick better for coding?

Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 26.6 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and Llama 4 Maverick share?

24 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Llama 4 Maverick has 54.