# Claude Sonnet 5 vs Gemma 4 26B A4B IT

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 37× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-gemma-4-26b-a4b-it
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and Gemma 4 26B A4B IT in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 21.8.
- The biggest single-benchmark swing is WeirdML: 68.8% for Claude Sonnet 5 and 35.2% for Gemma 4 26B A4B IT.
- Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 262K.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 54.6 | 43.5 |
| Rank | 29 | 92 |
| Context | 1M | 262K |
| Input $/M | $2 | $0.0675 |
| Output $/M | $10 | $0.23 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- Gemma 4 26B A4B IT: 39.0 (#164)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena WebDev | 1541 | 1359 |
| SciCode | 54.3% | 40% |
| WeirdML | 68.8% | 35.2% |
| LMArena Coding | 1483 | 1447 |
| ALE-Bench | 1,463 | 927.17 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- Gemma 4 26B A4B IT: —

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- Gemma 4 26B A4B IT: 21.8 (#213)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| CritPt | 16.9% | 0% |
| Chess Puzzles | 35% | 6% |
| LMArena Hard Prompts | 1461 | 1439 |
| DTBench | 92.5% | 74.9% |
| LMCA | 50% | 29.7% |
| Epoch Capabilities Index | 156.21 | 141.85 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |

## Math

- Claude Sonnet 5: 66.2 (#27)
- Gemma 4 26B A4B IT: 47.6 (#67)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 82.2% |
| LMArena Math | 1467 | 1470 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- Gemma 4 26B A4B IT: 45.7 (#85)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 90.5% | 73.2% |
| LMArena Expert | 1490 | 1447 |
| SimpleQA Verified | 33.7% | — |
| Vectara Hallucination Rate | — | 5.2% |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- Gemma 4 26B A4B IT: 40.6 (#46)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | 1274 | 1260 |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- Gemma 4 26B A4B IT: 53.1 (#71)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1431 | 1421 |
| LMArena Chinese | 1477 | 1495 |
| LMArena French | 1460 | 1460 |
| LMArena Russian | 1451 | 1434 |
| LMArena Spanish | 1437 | 1417 |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- Gemma 4 26B A4B IT: 74.8 (#82)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1452 | 1420 |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- Gemma 4 26B A4B IT: 43.6 (#91)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1463 | 1428 |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- Gemma 4 26B A4B IT: 58.6 (#115)

| Benchmark | Claude Sonnet 5 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1442 | 1434 |
| LMArena Creative Writing | 1416 | 1402 |
| EQ-Bench Creative Writing | 1794 | 1305 |
| LMArena Multi-Turn | 1454 | 1441 |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than Gemma 4 26B A4B IT?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 37× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5 or Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or Gemma 4 26B A4B IT better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 39.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 262K.

### How many benchmarks do Claude Sonnet 5 and Gemma 4 26B A4B IT share?

27 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemma 4 26B A4B IT has 28.