# Claude Sonnet 4.6 vs Gemma 2 9B

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-gemma-2-9b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Gemma 2 9B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 51.9 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 0.6% for Gemma 2 9B.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 50.1 | 25.7 |
| Rank | 42 | 334 |
| Context | 1M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.6: 46.0 (#62)
- Gemma 2 9B: 29.0 (#299)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Coding | 1504 | 1174 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1521 | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| BigCodeBench Instruct | — | 34.7% |
| LiveBench Coding | — | 22.5% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 1,327 | — |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#26)
- Gemma 2 9B: —

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#40)
- Gemma 2 9B: 15.3 (#306)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1172 |
| Epoch Capabilities Index | 152.25 | 119.78 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| LiveBench Reasoning | — | 15.2% |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 36.4% |
| LMCA | 46.5% | — |
| ForecastBench | 62 | — |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |

## Math

- Claude Sonnet 4.6: 51.9 (#41)
- Gemma 2 9B: 9.3 (#312)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 0.6% |
| LMArena Math | 1463 | 1183 |
| ProofBench | 45% | — |
| LiveBench Math | — | 19.8% |
| MATH Level 5 | — | 21% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
| GSM8K | — | 84.9% |

## Knowledge

- Claude Sonnet 4.6: 51.6 (#60)
- Gemma 2 9B: 9.7 (#300)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | 87.4% | 27.5% |
| LMArena Expert | 1500 | 1147 |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#61)
- Gemma 2 9B: —

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.6 (#39)
- Gemma 2 9B: 36.8 (#233)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1440 | 1188 |
| LMArena Chinese | 1491 | 1185 |
| LMArena French | 1465 | 1189 |
| LMArena German | 1428 | 1186 |
| LMArena Japanese | 1419 | 1144 |
| LMArena Korean | 1411 | 1137 |
| LMArena Russian | 1440 | 1200 |
| LMArena Spanish | 1465 | 1200 |

## Instruction Following

- Claude Sonnet 4.6: 77.6 (#23)
- Gemma 2 9B: 57.8 (#264)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Instruction Following | 1476 | 1178 |
| LiveBench Instruction Following | — | 52.6% |

## Long Context

- Claude Sonnet 4.6: 45.3 (#40)
- Gemma 2 9B: 36.3 (#228)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1479 | 1197 |

## Writing & Preference

- Claude Sonnet 4.6: 70.4 (#22)
- Gemma 2 9B: 32.3 (#276)

| Benchmark | Claude Sonnet 4.6 | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1458 | 1207 |
| LMArena Creative Writing | 1435 | 1206 |
| EQ-Bench Creative Writing | 1810 | 841 |
| LMArena Multi-Turn | 1464 | 1193 |
| EQ-Bench 4 | 1207 | — |
| LiveBench Language | — | 25.5% |

## FAQ

### Is Claude Sonnet 4.6 better than Gemma 2 9B?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 25.7 on the Noometry Index.

### Is Claude Sonnet 4.6 or Gemma 2 9B better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 29.0 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 4.6 and Gemma 2 9B share?

21 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemma 2 9B has 35.