# Claude Sonnet 4 vs Gemma 2 27B

> Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.4 on the Noometry Index. Gemma 2 27B costs 9.2× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-vs-gemma-2-27b
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Gemma 2 27B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 1.4% for Gemma 2 27B.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 40.8 | 29.4 |
| Rank | 145 | 312 |
| Context | 200K | 8K |
| Input $/M | $3 | $0.65 |
| Output $/M | $15 | $0.65 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4: 43.5 (#88)
- Gemma 2 27B: 34.1 (#246)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Coding | 1414 | 1211 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| BigCodeBench Instruct | — | 42.8% |
| LiveBench Coding | — | 36% |
| BigCodeBench Complete | — | 52.5% |
| ALE-Bench | 655.35 | — |

## Agentic & Tool Use

- Claude Sonnet 4: 38.5 (#31)
- Gemma 2 27B: —

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |

## Reasoning

- Claude Sonnet 4: 22.9 (#187)
- Gemma 2 27B: 15.3 (#315)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1198 |
| DTBench | 77.1% | 48% |
| LMCA | 29% | 7.1% |
| Epoch Capabilities Index | 141.69 | 122.08 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| LiveBench Reasoning | — | 28.1% |
| LiveBench Data Analysis | — | 47.9% |
| ForecastBench | 60.2 | — |
| LiveBench | — | 38.2% |

## Math

- Claude Sonnet 4: 43.3 (#80)
- Gemma 2 27B: 10.7 (#311)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 1.4% |
| LMArena Math | 1375 | 1212 |
| MATH Level 5 | 84.4% | 27.9% |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 26.5% |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Claude Sonnet 4: 41.8 (#108)
- Gemma 2 27B: 19.0 (#280)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| GPQA Diamond | 79.2% | 36.5% |
| Confabulations | 13.2% | 27.1% |
| LMArena Expert | 1372 | 1172 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| MMLU | — | 75.7% |

## Multimodal

- Claude Sonnet 4: 26.2 (#121)
- Gemma 2 27B: —

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |

## Multilingual

- Claude Sonnet 4: 46.7 (#156)
- Gemma 2 27B: 38.6 (#226)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1333 | 1217 |
| LMArena Chinese | 1350 | 1221 |
| LMArena French | 1363 | 1247 |
| LMArena German | 1331 | 1209 |
| LMArena Japanese | 1302 | 1175 |
| LMArena Korean | 1291 | 1174 |
| LMArena Russian | 1355 | 1234 |
| LMArena Spanish | 1357 | 1228 |

## Instruction Following

- Claude Sonnet 4: 71.7 (#145)
- Gemma 2 27B: 60.5 (#249)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1206 |
| LiveBench Instruction Following | — | 58.1% |
| IFEval | 84% | — |

## Long Context

- Claude Sonnet 4: 33.7 (#259)
- Gemma 2 27B: 37.3 (#218)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1398 | 1231 |
| Fiction.LiveBench | 46.9% | — |

## Writing & Preference

- Claude Sonnet 4: 57.1 (#132)
- Gemma 2 27B: 44.2 (#225)

| Benchmark | Claude Sonnet 4 | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1351 | 1231 |
| LMArena Creative Writing | 1345 | 1241 |
| LMArena Multi-Turn | 1376 | 1224 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 32.6% |

## FAQ

### Is Claude Sonnet 4 better than Gemma 2 27B?

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.4 on the Noometry Index. Gemma 2 27B costs 9.2× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4 or Gemma 2 27B?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

### Is Claude Sonnet 4 or Gemma 2 27B better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 4 does, with 200K tokens against 8K.

### How many benchmarks do Claude Sonnet 4 and Gemma 2 27B share?

24 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemma 2 27B has 34.