# Claude Sonnet 4.5 vs Gemini 3 Flash Preview

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-gemini-3-flash-preview
- Last updated: 2026-10-10
- Shared benchmarks: 53

## Summary

- They share 53 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 2 categories and Gemini 3 Flash Preview in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 26.9.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 83.1% 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 4.5.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 44.1 | 52.3 |
| Rank | 81 | 40 |
| Context | 200K | 1.05M |
| Input $/M | $3 | $0.50 |
| Output $/M | $15 | $3 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.3 (#61)
- Gemini 3 Flash Preview: 50.9 (#42)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| SWE-bench Verified | 71.3% | 75.4% |
| SWE-bench Verified (bash only) | 71.4% | 75.8% |
| LMArena WebDev | 1393 | 1439 |
| SWE-bench Multilingual | 67% | 72.7% |
| GSO | 14.7% | 9.8% |
| WeirdML | 47.7% | 61.6% |
| LMArena Coding | 1489 | 1460 |
| ALE-Bench | 796.15 | 1,367 |
| SciCode | 44.7% | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.3 (#32)
- Gemini 3 Flash Preview: 38.7 (#29)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | 46.5% | 64.3% |
| τ²-bench Airline | 72% | 82.5% |
| τ²-bench Banking | 25.3% | 27.3% |
| τ²-bench Retail | 72.4% | 76.8% |
| τ²-bench Telecom | 84.9% | 91.2% |
| DeepResearch Bench | 52.6% | 49.8% |
| LMArena Search | 1159 | 1198 |
| Vending-Bench 2 | 3,839 | 3,635 |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| Cybench | 60% | — |
| OSWorld | 62.9% | — |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| METR Time Horizons | 67.4% | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#125)
- Gemini 3 Flash Preview: 49.2 (#37)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| ARC-AGI-2 | 13.6% | 33.6% |
| SimpleBench | 54.3% | 61.1% |
| NYT Connections (extended) | 37.3% | 83.1% |
| ARC-AGI-1 | 63.7% | 84.7% |
| Chess Puzzles | 12% | 40% |
| LMArena Hard Prompts | 1462 | 1465 |
| Mystery Game Puzzles | 17% | 26% |
| DTBench | 83.2% | 89.1% |
| LMCA | 38.8% | 43.1% |
| Epoch Capabilities Index | 146.84 | 151.8 |
| ForecastBench | 61.9 | 58.5 |
| Kagi LLM Benchmark | 57.9% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |

## Math

- Claude Sonnet 4.5: 32.3 (#216)
- Gemini 3 Flash Preview: 51.7 (#55)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 51.2% |
| FrontierMath Tier 4 | 2.4% | 17.1% |
| OTIS Mock AIME 2024-2025 | 77.8% | 95.6% |
| ProofBench | 19% | 15% |
| LMArena Math | 1449 | 1473 |
| FrontierMath (Feb 2025 set) | 15.2% | 35.6% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| MathArena Final-Answer Competitions | — | 67.6% |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#76)
- Gemini 3 Flash Preview: 58.8 (#33)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | 82.3% | 89.4% |
| SimpleQA Verified | 30.7% | 66.8% |
| Vectara Hallucination Rate | 12% | 13.5% |
| LMArena Expert | 1482 | 1462 |
| Humanity's Last Exam | 13.7% | — |
| MMLU-Pro | 86.9% | — |
| GPQA (HELM) | 68.6% | — |

## Multimodal

- Claude Sonnet 4.5: 34.8 (#89)
- Gemini 3 Flash Preview: 45.5 (#16)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| VPCT | 39.8% | 72.6% |
| LMArena Document | 1450 | 1413 |
| LMArena Vision | — | 1285 |
| GeoBench | — | 88% |
| Blueprint-Bench 2 | — | 0% |

## Multilingual

- Claude Sonnet 4.5: 53.4 (#69)
- Gemini 3 Flash Preview: 55.7 (#27)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1425 | 1458 |
| LMArena Chinese | 1459 | 1511 |
| LMArena French | 1458 | 1477 |
| LMArena German | 1427 | 1497 |
| LMArena Japanese | 1390 | 1489 |
| LMArena Korean | 1403 | 1443 |
| LMArena Russian | 1437 | 1480 |
| LMArena Spanish | 1457 | 1469 |

## Instruction Following

- Claude Sonnet 4.5: 75.0 (#78)
- Gemini 3 Flash Preview: 75.7 (#56)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1459 | 1437 |
| IFEval | 85% | — |

## Long Context

- Claude Sonnet 4.5: 45.2 (#46)
- Gemini 3 Flash Preview: 44.4 (#67)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1476 | 1452 |

## Writing & Preference

- Claude Sonnet 4.5: 66.5 (#34)
- Gemini 3 Flash Preview: 65.5 (#45)

| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1439 | 1466 |
| LMArena Creative Writing | 1442 | 1457 |
| LMArena Multi-Turn | 1465 | 1471 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |

## FAQ

### Is Claude Sonnet 4.5 better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.1 on the Noometry Index.

### Which is cheaper, Claude Sonnet 4.5 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 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 47.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 200K.

### How many benchmarks do Claude Sonnet 4.5 and Gemini 3 Flash Preview share?

53 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 3 Flash Preview has 59.