# Claude 3.7 Sonnet vs Gemma 2 9B

> Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-gemma-2-9b
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 8 categories and Gemma 2 9B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3.7 Sonnet leads 39.7 to 9.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 87.8% for Claude 3.7 Sonnet and 15.2% for Gemma 2 9B.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 39.4 | 25.7 |
| Rank | 154 | 334 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- Gemma 2 9B: 29.0 (#299)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LiveBench Coding | 74.5% | 22.5% |
| LMArena Coding | 1361 | 1174 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| BigCodeBench Instruct | — | 34.7% |
| BigCodeBench Complete | — | 40.6% |
| CadEval | 54% | — |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- Gemma 2 9B: —

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| 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 2 9B: 15.3 (#306)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LiveBench Reasoning | 87.8% | 15.2% |
| LMArena Hard Prompts | 1333 | 1172 |
| LiveBench Data Analysis | 74% | 36.4% |
| Epoch Capabilities Index | 141.16 | 119.78 |
| LiveBench | 76.1% | 28.7% |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| ForecastBench | 61.8 | — |
| PIQA | — | 83.7% |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- Gemma 2 9B: 9.3 (#312)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 0.6% |
| LiveBench Math | 79% | 19.8% |
| LMArena Math | 1336 | 1183 |
| MATH Level 5 | 91.2% | 21% |
| Omni-MATH | 33% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| GSM8K | — | 84.9% |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- Gemma 2 9B: 9.7 (#300)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | 79.7% | 27.5% |
| LMArena Expert | 1321 | 1147 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- Gemma 2 9B: —

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- Gemma 2 9B: 36.8 (#233)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1296 | 1188 |
| LMArena Chinese | 1299 | 1185 |
| LMArena French | 1302 | 1189 |
| LMArena German | 1301 | 1186 |
| LMArena Japanese | 1268 | 1144 |
| LMArena Korean | 1249 | 1137 |
| LMArena Russian | 1311 | 1200 |
| LMArena Spanish | 1299 | 1200 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- Gemma 2 9B: 57.8 (#264)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 52.6% |
| LMArena Instruction Following | 1352 | 1178 |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- Gemma 2 9B: 36.3 (#228)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1373 | 1197 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- Gemma 2 9B: 32.3 (#276)

| Benchmark | Claude 3.7 Sonnet | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1314 | 1207 |
| LMArena Creative Writing | 1332 | 1206 |
| EQ-Bench Creative Writing | 1412 | 841 |
| LMArena Multi-Turn | 1339 | 1193 |
| LiveBench Language | 59.9% | 25.5% |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Gemma 2 9B?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 25.7 on the Noometry Index.

### Is Claude 3.7 Sonnet or Gemma 2 9B better for coding?

Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 29.0 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Gemma 2 9B share?

29 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemma 2 9B has 35.