# Claude Sonnet 4.6 vs Gemini 3 Flash Preview

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 50.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-gemini-3-flash-preview
- Last updated: 2026-10-10
- Shared benchmarks: 45

## Summary

- They share 45 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 5 categories and Gemini 3 Flash Preview in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 3 Flash Preview leads 45.3 to 38.0.
- The biggest single-benchmark swing is SimpleQA Verified: 35.5% for Claude Sonnet 4.6 and 66.8% for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 50.1 | 52.3 |
| Rank | 42 | 33 |
| Context | 1M | 1.05M |
| Input $/M | $3 | $0.50 |
| Output $/M | $15 | $3 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.6: 46.0 (#62)
- Gemini 3 Flash Preview: 51.5 (#35)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| SWE-bench Verified | 75.2% | 75.4% |
| LMArena WebDev | 1521 | 1439 |
| WeirdML | 66.1% | 61.6% |
| LMArena Coding | 1504 | 1460 |
| ALE-Bench | 1,327 | 1,367 |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 72.7% |
| SciCode | 46.8% | — |
| GSO | — | 9.8% |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#26)
- Gemini 3 Flash Preview: 38.6 (#27)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | 53.4% | 64.3% |
| DeepResearch Bench | 54.9% | 49.8% |
| GDP.pdf | 18% | 10% |
| LMArena Search | 1221 | 1198 |
| Vending-Bench 2 | 7,204 | 3,635 |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| OSWorld | 72.1% | — |
| BALROG | — | 48.1% |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#40)
- Gemini 3 Flash Preview: 49.2 (#35)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| ARC-AGI-2 | 60.4% | 33.6% |
| NYT Connections (extended) | 80.9% | 83.1% |
| ARC-AGI-1 | 86.5% | 84.7% |
| Chess Puzzles | 13% | 40% |
| LMArena Hard Prompts | 1485 | 1465 |
| Mystery Game Puzzles | 16% | 26% |
| DTBench | 89.9% | 89.1% |
| LMCA | 46.5% | 43.1% |
| Epoch Capabilities Index | 152.25 | 151.83 |
| ForecastBench | 62 | 58.5 |
| SimpleBench | — | 61.1% |
| CritPt | 3.1% | — |
| Thematic Generalization | 76.3% | — |

## Math

- Claude Sonnet 4.6: 51.9 (#41)
- Gemini 3 Flash Preview: 51.4 (#42)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 95.6% |
| ProofBench | 45% | 15% |
| LMArena Math | 1463 | 1472 |
| FrontierMath (Feb 2025 set) | 32.4% | 35.6% |
| FrontierMath Tier 4 (v1) | 8.3% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |

## Knowledge

- Claude Sonnet 4.6: 51.6 (#60)
- Gemini 3 Flash Preview: 58.8 (#30)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | 87.4% | 89.4% |
| SimpleQA Verified | 35.5% | 66.8% |
| Vectara Hallucination Rate | 10.6% | 13.5% |
| LMArena Expert | 1500 | 1461 |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#61)
- Gemini 3 Flash Preview: 45.3 (#15)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | 1283 | 1285 |
| Blueprint-Bench 2 | 6.7% | 0% |
| LMArena Document | 1482 | 1413 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |

## Multilingual

- Claude Sonnet 4.6: 54.6 (#39)
- Gemini 3 Flash Preview: 55.9 (#26)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1440 | 1458 |
| LMArena Chinese | 1491 | 1510 |
| LMArena French | 1465 | 1478 |
| LMArena German | 1428 | 1497 |
| LMArena Japanese | 1419 | 1488 |
| LMArena Korean | 1411 | 1443 |
| LMArena Russian | 1440 | 1480 |
| LMArena Spanish | 1465 | 1470 |

## Instruction Following

- Claude Sonnet 4.6: 77.6 (#23)
- Gemini 3 Flash Preview: 75.8 (#52)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1476 | 1437 |

## Long Context

- Claude Sonnet 4.6: 45.3 (#40)
- Gemini 3 Flash Preview: 44.4 (#63)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1479 | 1452 |

## Writing & Preference

- Claude Sonnet 4.6: 70.4 (#22)
- Gemini 3 Flash Preview: 65.6 (#44)

| Benchmark | Claude Sonnet 4.6 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1458 | 1466 |
| LMArena Creative Writing | 1435 | 1457 |
| LMArena Multi-Turn | 1464 | 1471 |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |

## FAQ

### Is Claude Sonnet 4.6 better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 50.1 on the Noometry Index.

### Which is cheaper, Claude Sonnet 4.6 or Gemini 3 Flash Preview?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

### Is Claude Sonnet 4.6 or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 46.0 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Sonnet 4.6 and Gemini 3 Flash Preview share?

45 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemini 3 Flash Preview has 59.