# Claude Sonnet 5 vs Gemini 3.6 Flash

> Claude Sonnet 5 and Gemini 3.6 Flash score almost the same on the Noometry Index (54.5 vs 54.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-gemini-3-6-flash
- Last updated: 2026-10-10
- Shared benchmarks: 41

## Summary

- They share 41 benchmarks with published results for both. Claude Sonnet 5 scores higher in 5 categories and Gemini 3.6 Flash in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.6 Flash leads 67.8 to 55.7.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 36% for Gemini 3.6 Flash.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 54.5 | 54.1 |
| Rank | 26 | 30 |
| Context | 1M | 1.05M |
| Input $/M | $2 | $0.75 |
| Output $/M | $10 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#20)
- Gemini 3.6 Flash: 49.6 (#45)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| DeepSWE | 53.8% | 46.7% |
| FrontierCode | 42.7% | 34.4% |
| LMArena WebDev | 1540 | 1536 |
| SciCode | 53.6% | 52.7% |
| WeirdML | 68.8% | 56.1% |
| LMArena Coding | 1483 | 1492 |
| ALE-Bench | 1,463 | 715.52 |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.7 (#16)
- Gemini 3.6 Flash: 32.4 (#56)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | 54.5% | 46.9% |
| GBAEval | 65.3% | — |
| GDP.pdf | — | 14% |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 48.2 (#37)
- Gemini 3.6 Flash: 58.9 (#20)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| NYT Connections (extended) | 75.1% | 89% |
| CritPt | 16.9% | 10.6% |
| Chess Puzzles | 35% | 43% |
| LMArena Hard Prompts | 1461 | 1486 |
| Mystery Game Puzzles | 35% | 30% |
| DTBench | 92.5% | 95.5% |
| LMCA | 50% | 44.9% |
| Epoch Capabilities Index | 156.34 | 154.36 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | 60.6% | — |
| ARC-AGI-1 | — | 91.2% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |

## Math

- Claude Sonnet 5: 66.1 (#21)
- Gemini 3.6 Flash: 57.0 (#33)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 58.9% |
| FrontierMath Tier 4 | 29.3% | 22% |
| OTIS Mock AIME 2024-2025 | 94.7% | 94.2% |
| ProofBench | 77% | 36% |
| LMArena Math | 1467 | 1504 |
| MathArena Final-Answer Competitions | — | 70.8% |

## Knowledge

- Claude Sonnet 5: 55.7 (#42)
- Gemini 3.6 Flash: 67.8 (#7)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 90.5% | 94.1% |
| SimpleQA Verified | 33.7% | 66.2% |
| LMArena Expert | 1491 | 1489 |

## Multimodal

- Claude Sonnet 5: 42.4 (#26)
- Gemini 3.6 Flash: 38.7 (#55)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | 1275 | 1297 |
| Blueprint-Bench 2 | 24.9% | 31.2% |
| LMArena Document | 1466 | 1456 |
| Furniture Assembly | — | 23.3% |

## Multilingual

- Claude Sonnet 5: 54.0 (#55)
- Gemini 3.6 Flash: 56.8 (#17)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1431 | 1470 |
| LMArena Chinese | 1475 | 1530 |
| LMArena French | 1457 | 1501 |
| LMArena German | 1448 | 1478 |
| LMArena Japanese | 1422 | 1477 |
| LMArena Korean | 1411 | 1435 |
| LMArena Russian | 1452 | 1490 |
| LMArena Spanish | 1436 | 1477 |

## Instruction Following

- Claude Sonnet 5: 76.6 (#39)
- Gemini 3.6 Flash: 77.2 (#27)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1453 | 1467 |

## Long Context

- Claude Sonnet 5: 44.8 (#53)
- Gemini 3.6 Flash: 45.1 (#47)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1464 | 1475 |

## Writing & Preference

- Claude Sonnet 5: 69.4 (#24)
- Gemini 3.6 Flash: 68.3 (#26)

| Benchmark | Claude Sonnet 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1443 | 1478 |
| LMArena Creative Writing | 1416 | 1464 |
| EQ-Bench Creative Writing | 1794 | 1604 |
| LMArena Multi-Turn | 1454 | 1481 |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than Gemini 3.6 Flash?

Claude Sonnet 5 and Gemini 3.6 Flash score almost the same on the Noometry Index (54.5 vs 54.1), so choose on price, context window or the category you care about most.

### Which is cheaper, Claude Sonnet 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 5 lists at $2 and $10.

### Is Claude Sonnet 5 or Gemini 3.6 Flash better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 49.6 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 5 and Gemini 3.6 Flash share?

41 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemini 3.6 Flash has 46.