# Claude 3.7 Sonnet vs Gemma 3 4B

> Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-gemma-3-4b
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 9 categories and Gemma 3 4B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3.7 Sonnet leads 39.7 to 11.8.
- The biggest single-benchmark swing is GPQA Diamond: 79.7% for Claude 3.7 Sonnet and 23.2% for Gemma 3 4B.
- Gemma 3 4B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 39.4 | 27.9 |
| Rank | 154 | 320 |
| Context | — | 131K |
| Input $/M | — | $0.04 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- Gemma 3 4B: 35.3 (#214)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1361 | 1230 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- Gemma 3 4B: 20.7 (#134)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- Gemma 3 4B: 12.7 (#330)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1253 |
| Epoch Capabilities Index | 141.16 | 116.02 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 25.2% |
| ARC-AGI-1 | 28.6% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 50.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 2.8% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- Gemma 3 4B: 15.8 (#286)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 7.5% |
| LMArena Math | 1336 | 1239 |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- Gemma 3 4B: 11.8 (#294)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | 79.7% | 23.2% |
| LMArena Expert | 1321 | 1223 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 6.4% |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- Gemma 3 4B: —

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- Gemma 3 4B: 42.7 (#189)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1296 | 1273 |
| LMArena German | 1301 | 1281 |
| LMArena Russian | 1311 | 1294 |
| LMArena Chinese | 1299 | — |
| LMArena French | 1302 | — |
| LMArena Japanese | 1268 | — |
| LMArena Korean | 1249 | — |
| LMArena Spanish | 1299 | — |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- Gemma 3 4B: 65.4 (#219)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1239 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- Gemma 3 4B: 38.6 (#189)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1373 | 1274 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- Gemma 3 4B: 42.2 (#234)

| Benchmark | Claude 3.7 Sonnet | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1314 | 1291 |
| LMArena Creative Writing | 1332 | 1270 |
| EQ-Bench Creative Writing | 1412 | 1068 |
| LMArena Multi-Turn | 1339 | 1255 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Gemma 3 4B?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 27.9 on the Noometry Index.

### Is Claude 3.7 Sonnet or Gemma 3 4B better for coding?

Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 35.3 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Gemma 3 4B share?

16 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemma 3 4B has 22.