# Claude Sonnet 5 vs Gemini 3.7 Flash

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 54.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-gemini-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. Claude Sonnet 5 scores higher in 2 categories and Gemini 3.7 Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 49.1.
- The biggest single-benchmark swing is SimpleQA Verified: 33.7% for Claude Sonnet 5 and 69.2% for Gemini 3.7 Flash.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 54.6 | 59.8 |
| Rank | 29 | 14 |
| Context | 1M | 1.05M |
| Input $/M | $2 | $0.75 |
| Output $/M | $10 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- Gemini 3.7 Flash: 56.2 (#22)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| DeepSWE | 53.8% | 65.5% |
| FrontierCode | 42.7% | 43.6% |
| LMArena WebDev | 1541 | 1592 |
| SciCode | 54.3% | 59.8% |
| LMArena Coding | 1483 | 1497 |
| ALE-Bench | 1,463 | 904.3 |
| CursorBench | 34.1% | — |
| FrontierSWE | — | 20.3% |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- Gemini 3.7 Flash: 42.1 (#19)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | 54.5% | 67.8% |
| Remote Labor Index | — | 5% |
| GBAEval | 65.3% | — |
| GDP.pdf | — | 23.8% |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- Gemini 3.7 Flash: 70.0 (#15)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 75.1% | 94% |
| CritPt | 16.9% | 14.3% |
| Chess Puzzles | 35% | 47% |
| LMArena Hard Prompts | 1461 | 1494 |
| Mystery Game Puzzles | 35% | 37% |
| DTBench | 92.5% | 96.8% |
| LMCA | 50% | 50.4% |
| Epoch Capabilities Index | 156.21 | 157.27 |
| ARC-AGI-2 | — | 84.6% |
| SimpleBench | 60.6% | — |
| ARC-AGI-1 | — | 95.5% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |

## Math

- Claude Sonnet 5: 66.2 (#27)
- Gemini 3.7 Flash: 69.6 (#23)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 71.6% |
| FrontierMath Tier 4 | 29.3% | 36.6% |
| OTIS Mock AIME 2024-2025 | 94.7% | 97.2% |
| ProofBench | 77% | 58% |
| LMArena Math | 1467 | 1507 |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- Gemini 3.7 Flash: 69.7 (#5)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 90.5% | 94.8% |
| SimpleQA Verified | 33.7% | 69.2% |
| LMArena Expert | 1490 | 1508 |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- Gemini 3.7 Flash: 37.3 (#73)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1274 | 1316 |
| Blueprint-Bench 2 | 24.9% | — |
| Furniture Assembly | — | 26.7% |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- Gemini 3.7 Flash: 57.6 (#7)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1431 | 1484 |
| LMArena Chinese | 1477 | 1548 |
| LMArena French | 1460 | 1505 |
| LMArena German | 1440 | 1498 |
| LMArena Japanese | 1422 | 1512 |
| LMArena Korean | 1411 | 1483 |
| LMArena Russian | 1451 | 1516 |
| LMArena Spanish | 1437 | 1503 |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- Gemini 3.7 Flash: 77.7 (#15)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1452 | 1483 |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- Gemini 3.7 Flash: 45.7 (#30)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1463 | 1492 |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- Gemini 3.7 Flash: 71.2 (#20)

| Benchmark | Claude Sonnet 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1442 | 1486 |
| LMArena Creative Writing | 1416 | 1490 |
| EQ-Bench Creative Writing | 1794 | 1723 |
| LMArena Multi-Turn | 1454 | 1489 |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 54.6 on the Noometry Index.

### Which is cheaper, Claude Sonnet 5 or Gemini 3.7 Flash?

Gemini 3.7 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 3.7 Flash better for coding?

They score almost the same on coding (55.5 vs 56.2); test both on your own repository before choosing.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Sonnet 5 and Gemini 3.7 Flash share?

38 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemini 3.7 Flash has 44.