# Claude Sonnet 4.5 vs Gemini 3.6 Flash

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 44.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-gemini-3-6-flash
- Last updated: 2026-10-10
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 2 categories and Gemini 3.6 Flash in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 26.9.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 89% for Gemini 3.6 Flash.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 44.0 | 54.1 |
| Rank | 76 | 30 |
| Context | 1M | 1.05M |
| Input $/M | $3 | $0.75 |
| Output $/M | $15 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.8 (#54)
- Gemini 3.6 Flash: 49.6 (#45)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena WebDev | 1393 | 1536 |
| SciCode | 44.7% | 52.7% |
| WeirdML | 47.7% | 56.1% |
| LMArena Coding | 1489 | 1492 |
| ALE-Bench | 796.15 | 715.52 |
| SWE-bench Verified | 71.3% | — |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.1 (#30)
- Gemini 3.6 Flash: 32.4 (#56)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| APEX-Agents | — | 46.9% |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| GDP.pdf | — | 14% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#113)
- Gemini 3.6 Flash: 58.9 (#20)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| ARC-AGI-2 | 13.6% | 60.4% |
| NYT Connections (extended) | 37.3% | 89% |
| ARC-AGI-1 | 63.7% | 91.2% |
| CritPt | 1.1% | 10.6% |
| Chess Puzzles | 12% | 43% |
| LMArena Hard Prompts | 1462 | 1486 |
| Mystery Game Puzzles | 17% | 30% |
| DTBench | 83.2% | 95.5% |
| LMCA | 38.8% | 44.9% |
| Epoch Capabilities Index | 146.84 | 154.36 |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| ForecastBench | 61.9 | — |

## Math

- Claude Sonnet 4.5: 31.9 (#190)
- Gemini 3.6 Flash: 57.0 (#33)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 58.9% |
| FrontierMath Tier 4 | 2.4% | 22% |
| OTIS Mock AIME 2024-2025 | 77.8% | 94.2% |
| ProofBench | 19% | 36% |
| LMArena Math | 1448 | 1504 |
| MathArena Final-Answer Competitions | — | 70.8% |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#70)
- Gemini 3.6 Flash: 67.8 (#7)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 82.3% | 94.1% |
| SimpleQA Verified | 30.7% | 66.2% |
| LMArena Expert | 1483 | 1489 |
| Humanity's Last Exam | 13.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |

## Multimodal

- Claude Sonnet 4.5: 34.1 (#84)
- Gemini 3.6 Flash: 38.7 (#55)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Document | 1450 | 1456 |
| LMArena Vision | — | 1297 |
| VPCT | 39.8% | — |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |

## Multilingual

- Claude Sonnet 4.5: 53.6 (#65)
- Gemini 3.6 Flash: 56.8 (#17)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1425 | 1470 |
| LMArena Chinese | 1459 | 1530 |
| LMArena French | 1459 | 1501 |
| LMArena German | 1427 | 1478 |
| LMArena Japanese | 1390 | 1477 |
| LMArena Korean | 1403 | 1435 |
| LMArena Russian | 1436 | 1490 |
| LMArena Spanish | 1457 | 1477 |

## Instruction Following

- Claude Sonnet 4.5: 75.2 (#74)
- Gemini 3.6 Flash: 77.2 (#27)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1459 | 1467 |
| IFEval | 85% | — |

## Long Context

- Claude Sonnet 4.5: 45.2 (#45)
- Gemini 3.6 Flash: 45.1 (#47)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1476 | 1475 |

## Writing & Preference

- Claude Sonnet 4.5: 66.7 (#33)
- Gemini 3.6 Flash: 68.3 (#26)

| Benchmark | Claude Sonnet 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1439 | 1478 |
| LMArena Creative Writing | 1442 | 1464 |
| EQ-Bench Creative Writing | 1678 | 1604 |
| LMArena Multi-Turn | 1465 | 1481 |
| WildBench | 85.4% | — |

## FAQ

### Is Claude Sonnet 4.5 better than Gemini 3.6 Flash?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 44.0 on the Noometry Index.

### Which is cheaper, Claude Sonnet 4.5 or Gemini 3.6 Flash?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or Gemini 3.6 Flash better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 47.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Sonnet 4.5 and Gemini 3.6 Flash share?

38 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 3.6 Flash has 46.