# Gemma 2 9B vs Qwen3-Next 80B-A3B Instruct

> Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-qwen3-next-80b-a3b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Qwen3-Next 80B-A3B Instruct in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.8 to 9.7.

## Snapshot

| | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 25.9 | 43.0 |
| Rank | 341 | 102 |
| Context | — | 131K |
| Input $/M | — | $0.50 |
| Output $/M | — | $2 |
| Weights | Open | Open |

## Coding

- Gemma 2 9B: 29.4 (#304)
- Qwen3-Next 80B-A3B Instruct: 42.5 (#98)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1173 | 1440 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- Qwen3-Next 80B-A3B Instruct: 31.1 (#81)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- Qwen3-Next 80B-A3B Instruct: 38.8 (#126)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1183 | 1440 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| Omni-MATH | — | 46.7% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- Qwen3-Next 80B-A3B Instruct: 41.8 (#106)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1147 | 1417 |
| GPQA Diamond | 27.5% | — |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- Qwen3-Next 80B-A3B Instruct: 52.1 (#93)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1188 | 1407 |
| LMArena Chinese | 1185 | 1460 |
| LMArena French | 1190 | 1413 |
| LMArena German | 1186 | 1417 |
| LMArena Japanese | 1144 | 1395 |
| LMArena Korean | 1137 | 1364 |
| LMArena Russian | 1200 | 1404 |
| LMArena Spanish | 1200 | 1435 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- Qwen3-Next 80B-A3B Instruct: 70.8 (#159)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1178 | 1389 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 81% |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- Qwen3-Next 80B-A3B Instruct: 37.0 (#223)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1197 | 1403 |
| Fiction.LiveBench | — | 55.6% |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- Qwen3-Next 80B-A3B Instruct: 58.0 (#121)

| Benchmark | Gemma 2 9B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1207 | 1417 |
| LMArena Creative Writing | 1206 | 1334 |
| LMArena Multi-Turn | 1193 | 1416 |
| EQ-Bench Creative Writing | 841 | — |
| WildBench | — | 80.7% |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than Qwen3-Next 80B-A3B Instruct?

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 25.9 on the Noometry Index.

### Is Gemma 2 9B or Qwen3-Next 80B-A3B Instruct better for coding?

Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and Qwen3-Next 80B-A3B Instruct share?

17 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.