# Claude Sonnet 5.5 vs Gemini 3 Flash Preview

> Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 3.6× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-gemini-3-flash-preview
- Last updated: 2026-10-12
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 9 categories and Gemini 3 Flash Preview in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 51.7.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Sonnet 5.5 and 15% for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 61.9 | 52.3 |
| Rank | 10 | 40 |
| Context | 1M | 1.05M |
| Input $/M | $2 | $0.50 |
| Output $/M | $10 | $3 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5.5: 67.3 (#6)
- Gemini 3 Flash Preview: 50.9 (#42)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena WebDev | 1774 | 1439 |
| LMArena Coding | 1513 | 1460 |
| ALE-Bench | 1,819 | 1,367 |
| SWE-bench Verified | — | 75.4% |
| FrontierCode | 52.1% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| CursorBench | 55.5% | — |
| SWE-bench Multilingual | — | 72.7% |
| FrontierSWE | 61.9% | — |
| SciCode | 61% | — |
| GSO | — | 9.8% |
| WeirdML | — | 61.6% |

## Agentic & Tool Use

- Claude Sonnet 5.5: 45.0 (#16)
- Gemini 3 Flash Preview: 38.7 (#29)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | — | 64.3% |
| APEX-Agents | 75.5% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |

## Reasoning

- Claude Sonnet 5.5: 54.0 (#28)
- Gemini 3 Flash Preview: 49.2 (#37)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| NYT Connections (extended) | 80.5% | 83.1% |
| LMArena Hard Prompts | 1495 | 1465 |
| Mystery Game Puzzles | 65% | 26% |
| Epoch Capabilities Index | 165.03 | 151.8 |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| ARC-AGI-1 | — | 84.7% |
| CritPt | 31.4% | — |
| Chess Puzzles | — | 40% |
| DTBench | — | 89.1% |
| LMCA | — | 43.1% |
| ForecastBench | — | 58.5 |

## Math

- Claude Sonnet 5.5: 87.9 (#6)
- Gemini 3 Flash Preview: 51.7 (#55)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 88.8% | 51.2% |
| FrontierMath Tier 4 | 80.5% | 17.1% |
| OTIS Mock AIME 2024-2025 | 100% | 95.6% |
| ProofBench | 100% | 15% |
| LMArena Math | 1510 | 1473 |
| MathArena Final-Answer Competitions | — | 67.6% |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Erdős | 2.9% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#12)
- Gemini 3 Flash Preview: 58.8 (#33)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | 95.6% | 89.4% |
| SimpleQA Verified | 46.5% | 66.8% |
| LMArena Expert | 1540 | 1462 |
| Vectara Hallucination Rate | — | 13.5% |

## Multimodal

- Claude Sonnet 5.5: 51.5 (#6)
- Gemini 3 Flash Preview: 45.5 (#16)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | 1289 | 1285 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| Furniture Assembly | 75% | — |
| LMArena Document | — | 1413 |

## Multilingual

- Claude Sonnet 5.5: 55.3 (#30)
- Gemini 3 Flash Preview: 55.7 (#27)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1452 | 1458 |
| LMArena Chinese | 1522 | 1511 |
| LMArena Russian | 1451 | 1480 |
| LMArena French | — | 1477 |
| LMArena German | — | 1497 |
| LMArena Japanese | — | 1489 |
| LMArena Korean | — | 1443 |
| LMArena Spanish | — | 1469 |

## Instruction Following

- Claude Sonnet 5.5: 78.3 (#11)
- Gemini 3 Flash Preview: 75.7 (#56)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1495 | 1437 |

## Long Context

- Claude Sonnet 5.5: 45.9 (#28)
- Gemini 3 Flash Preview: 44.4 (#67)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1498 | 1452 |

## Writing & Preference

- Claude Sonnet 5.5: 66.0 (#40)
- Gemini 3 Flash Preview: 65.5 (#45)

| Benchmark | Claude Sonnet 5.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1471 | 1466 |
| LMArena Creative Writing | 1465 | 1457 |
| LMArena Multi-Turn | 1474 | 1471 |

## FAQ

### Is Claude Sonnet 5.5 better than Gemini 3 Flash Preview?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 3.6× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5.5 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 5.5 lists at $2 and $10.

### Is Claude Sonnet 5.5 or Gemini 3 Flash Preview better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 50.9 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 5.5 and Gemini 3 Flash Preview share?

24 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and Gemini 3 Flash Preview has 59.