# Gemma 2 9B vs Gemma 4 26B A4B IT

> Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-gemma-4-26b-a4b-it
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Gemma 4 26B A4B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 45.7 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 82.2% for Gemma 4 26B A4B IT.

## Snapshot

| | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 25.7 | 43.1 |
| Rank | 334 | 88 |
| Context | — | 262K |
| Input $/M | — | $0.0765 |
| Output $/M | — | $0.26 |
| Weights | Open | Open |

## Coding

- Gemma 2 9B: 29.0 (#299)
- Gemma 4 26B A4B IT: 38.8 (#156)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Coding | 1174 | 1446 |
| LMArena WebDev | — | 1359 |
| SciCode | — | 40% |
| WeirdML | — | 35.2% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 927.17 |

## Reasoning

- Gemma 2 9B: 15.3 (#306)
- Gemma 4 26B A4B IT: 21.1 (#205)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1438 |
| Epoch Capabilities Index | 119.78 | 141.85 |
| CritPt | — | 0% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 74.9% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 29.7% |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.3 (#312)
- Gemma 4 26B A4B IT: 45.7 (#61)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 82.2% |
| LMArena Math | 1183 | 1469 |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#300)
- Gemma 4 26B A4B IT: 45.6 (#79)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 27.5% | 73.2% |
| LMArena Expert | 1147 | 1447 |
| Vectara Hallucination Rate | — | 5.2% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multimodal

- Gemma 2 9B: —
- Gemma 4 26B A4B IT: 39.9 (#43)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | — | 1260 |

## Multilingual

- Gemma 2 9B: 36.8 (#233)
- Gemma 4 26B A4B IT: 53.3 (#68)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1188 | 1422 |
| LMArena Chinese | 1185 | 1495 |
| LMArena French | 1189 | 1459 |
| LMArena Russian | 1200 | 1434 |
| LMArena Spanish | 1200 | 1415 |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |

## Instruction Following

- Gemma 2 9B: 57.8 (#264)
- Gemma 4 26B A4B IT: 75.0 (#78)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1178 | 1420 |
| LiveBench Instruction Following | 52.6% | — |

## Long Context

- Gemma 2 9B: 36.3 (#228)
- Gemma 4 26B A4B IT: 43.6 (#87)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1197 | 1427 |

## Writing & Preference

- Gemma 2 9B: 32.3 (#276)
- Gemma 4 26B A4B IT: 58.8 (#110)

| Benchmark | Gemma 2 9B | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1207 | 1434 |
| LMArena Creative Writing | 1206 | 1401 |
| EQ-Bench Creative Writing | 841 | 1305 |
| LMArena Multi-Turn | 1193 | 1442 |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 25.7 on the Noometry Index.

### Is Gemma 2 9B or Gemma 4 26B A4B IT better for coding?

Gemma 4 26B A4B IT scores higher on coding benchmarks: 38.8 versus 29.0 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and Gemma 4 26B A4B IT share?

18 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Gemma 4 26B A4B IT has 28.
