# Claude 3.7 Sonnet vs Gemma 4 31B IT

> Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-gemma-4-31b-it
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 2 categories and Gemma 4 31B IT in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 4 31B IT leads 53.8 to 44.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 73.3% for Gemma 4 31B IT.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 39.5 | 43.5 |
| Rank | 164 | 90 |
| Context | — | 262K |
| Input $/M | — | $0.09 |
| Output $/M | — | $0.34 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.7 Sonnet: 40.6 (#136)
- Gemma 4 31B IT: 42.3 (#108)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1361 | 1459 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |
| GSO | 3.8% | — |
| WeirdML | — | 52.3% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 925.5 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 34.1 (#50)
- Gemma 4 31B IT: —

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |

## Reasoning

- Claude 3.7 Sonnet: 18.6 (#277)
- Gemma 4 31B IT: 27.2 (#122)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1448 |
| Epoch Capabilities Index | 141.16 | 142.74 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| EnigmaEval | 4.2% | — |
| Thematic Generalization | — | 53% |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 82.7% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 37.5 (#153)
- Gemma 4 31B IT: 43.2 (#81)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 73.3% |
| LMArena Math | 1337 | 1465 |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |

## Knowledge

- Claude 3.7 Sonnet: 39.8 (#130)
- Gemma 4 31B IT: 37.9 (#151)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 79.7% | 75.8% |
| LMArena Expert | 1321 | 1465 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 10.4% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 7.4% |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.7 (#95)
- Gemma 4 31B IT: 41.6 (#34)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1169 | 1277 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| LMArena Document | — | 1425 |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.1 (#179)
- Gemma 4 31B IT: 53.8 (#57)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1296 | 1431 |
| LMArena Chinese | 1299 | 1476 |
| LMArena French | 1303 | 1435 |
| LMArena Russian | 1311 | 1460 |
| LMArena Spanish | 1298 | 1444 |
| LMArena German | 1301 | — |
| LMArena Japanese | 1267 | — |
| LMArena Korean | 1249 | — |

## Instruction Following

- Claude 3.7 Sonnet: 72.9 (#125)
- Gemma 4 31B IT: 75.5 (#61)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1352 | 1433 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.3 (#10)
- Gemma 4 31B IT: 44.2 (#71)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1373 | 1446 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.4 (#150)
- Gemma 4 31B IT: 60.5 (#96)

| Benchmark | Claude 3.7 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1314 | 1443 |
| LMArena Creative Writing | 1332 | 1415 |
| EQ-Bench Creative Writing | 1412 | 1368 |
| LMArena Multi-Turn | 1339 | 1452 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| EQ-Bench 4 | — | 1120 |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.5 on the Noometry Index.

### Is Claude 3.7 Sonnet or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.6 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Gemma 4 31B IT share?

19 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemma 4 31B IT has 35.