# Claude 3 Sonnet vs Gemma 3 4B

> Claude 3 Sonnet and Gemma 3 4B score almost the same on the Noometry Index (29.0 vs 28.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-gemma-3-4b
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Claude 3 Sonnet scores higher in 3 categories and Gemma 3 4B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3 Sonnet leads 21.1 to 11.8.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Claude 3 Sonnet and 23.2% for Gemma 3 4B.
- Gemma 3 4B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 29.0 | 28.1 |
| Rank | 319 | 326 |
| Context | — | 131K |
| Input $/M | — | $0.04 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.6 (#302)
- Gemma 3 4B: 35.9 (#215)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1223 | 1230 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Gemma 3 4B: 20.9 (#142)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |

## Reasoning

- Claude 3 Sonnet: 20.5 (#237)
- Gemma 3 4B: 13.2 (#335)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1253 |
| DTBench | 53.6% | 50.9% |
| Epoch Capabilities Index | 120.7 | 116.02 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| LMCA | — | 2.8% |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.7 (#310)
- Gemma 3 4B: 16.8 (#292)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 7.5% |
| LMArena Math | 1213 | 1239 |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#276)
- Gemma 3 4B: 11.8 (#299)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | 40.6% | 23.2% |
| LMArena Expert | 1173 | 1223 |
| Vectara Hallucination Rate | — | 6.4% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 25.2 (#125)
- Gemma 3 4B: —

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 37.8 (#234)
- Gemma 3 4B: 42.5 (#194)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1205 | 1273 |
| LMArena German | 1204 | 1281 |
| LMArena Russian | 1227 | 1294 |
| LMArena Chinese | 1189 | — |
| LMArena French | 1229 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Spanish | 1204 | — |

## Instruction Following

- Claude 3 Sonnet: 62.8 (#235)
- Gemma 3 4B: 65.2 (#225)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1239 |

## Long Context

- Claude 3 Sonnet: 36.7 (#228)
- Gemma 3 4B: 38.7 (#194)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1211 | 1273 |

## Writing & Preference

- Claude 3 Sonnet: 42.1 (#238)
- Gemma 3 4B: 42.0 (#239)

| Benchmark | Claude 3 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1218 | 1291 |
| LMArena Creative Writing | 1186 | 1271 |
| LMArena Multi-Turn | 1227 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |

## FAQ

### Is Claude 3 Sonnet better than Gemma 3 4B?

Claude 3 Sonnet and Gemma 3 4B score almost the same on the Noometry Index (29.0 vs 28.1), so choose on price, context window or the category you care about most.

### Is Claude 3 Sonnet or Gemma 3 4B better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 29.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Gemma 3 4B share?

16 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 3 4B has 22.
