# Gemma 4 26B A4B IT vs Qwen2.5-Max

> Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 40.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-26b-a4b-it-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 6 categories and Qwen2.5-Max in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 36.9.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 43.5 | 40.7 |
| Rank | 92 | 146 |
| Context | 262K | — |
| Input $/M | $0.0675 | — |
| Output $/M | $0.23 | — |
| Weights | Open | Proprietary |

## Coding

- Gemma 4 26B A4B IT: 39.0 (#164)
- Qwen2.5-Max: 41.8 (#117)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1447 | 1359 |
| LMArena WebDev | 1359 | — |
| SciCode | 40% | — |
| WeirdML | 35.2% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 927.17 | — |

## Reasoning

- Gemma 4 26B A4B IT: 21.8 (#213)
- Qwen2.5-Max: 25.6 (#147)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1439 | 1360 |
| Epoch Capabilities Index | 141.85 | 132.53 |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 74.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 29.7% | — |
| LiveBench | — | 62.3% |

## Math

- Gemma 4 26B A4B IT: 47.6 (#67)
- Qwen2.5-Max: 36.9 (#162)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1470 | 1369 |
| OTIS Mock AIME 2024-2025 | 82.2% | — |
| LiveBench Math | — | 58.4% |

## Knowledge

- Gemma 4 26B A4B IT: 45.7 (#85)
- Qwen2.5-Max: 35.3 (#186)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1447 | 1337 |
| GPQA Diamond | 73.2% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 5.2% | — |

## Multimodal

- Gemma 4 26B A4B IT: 40.6 (#46)
- Qwen2.5-Max: —

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1260 | — |

## Multilingual

- Gemma 4 26B A4B IT: 53.1 (#71)
- Qwen2.5-Max: 48.1 (#146)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1421 | 1352 |
| LMArena Chinese | 1495 | 1382 |
| LMArena French | 1460 | 1396 |
| LMArena Russian | 1434 | 1353 |
| LMArena Spanish | 1417 | 1377 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1304 |

## Instruction Following

- Gemma 4 26B A4B IT: 74.8 (#82)
- Qwen2.5-Max: 71.3 (#152)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1420 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- Gemma 4 26B A4B IT: 43.6 (#91)
- Qwen2.5-Max: 41.4 (#142)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1428 | 1358 |

## Writing & Preference

- Gemma 4 26B A4B IT: 58.6 (#115)
- Qwen2.5-Max: 55.4 (#146)

| Benchmark | Gemma 4 26B A4B IT | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1434 | 1367 |
| LMArena Creative Writing | 1402 | 1339 |
| LMArena Multi-Turn | 1441 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1305 | — |
| LiveBench Language | — | 56.3% |

## FAQ

### Is Gemma 4 26B A4B IT better than Qwen2.5-Max?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 40.7 on the Noometry Index.

### Is Gemma 4 26B A4B IT or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 39.0 in the Noometry coding category.

### How many benchmarks do Gemma 4 26B A4B IT and Qwen2.5-Max share?

15 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Qwen2.5-Max has 27.