# Gemini 3.5 Flash vs Gemini 3.7 Flash

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 54.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-vs-gemini-3-7-flash
- Last updated: 2026-10-11
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 1 category and Gemini 3.7 Flash in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 3.7 Flash leads 42.1 to 24.7.
- The biggest single-benchmark swing is APEX-Agents: 27.5% for Gemini 3.5 Flash and 67.8% for Gemini 3.7 Flash.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.50 / $9 for Gemini 3.5 Flash.

## Snapshot

| | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 54.2 | 59.8 |
| Rank | 32 | 14 |
| Context | 1.05M | 1.05M |
| Input $/M | $1.50 | $0.75 |
| Output $/M | $9 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.5 Flash: 49.4 (#49)
- Gemini 3.7 Flash: 56.2 (#22)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| DeepSWE | 37.4% | 65.5% |
| LMArena WebDev | 1499 | 1592 |
| SciCode | 53.1% | 59.8% |
| LMArena Coding | 1492 | 1497 |
| ALE-Bench | 911.02 | 904.3 |
| SWE-bench Verified | 79.3% | — |
| FrontierCode | — | 43.6% |
| FrontierSWE | — | 20.3% |
| WeirdML | 62.6% | — |

## Agentic & Tool Use

- Gemini 3.5 Flash: 24.7 (#114)
- Gemini 3.7 Flash: 42.1 (#19)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | 27.5% | 67.8% |
| GDP.pdf | 14% | 23.8% |
| Remote Labor Index | — | 5% |
| GBAEval | 6.7% | — |
| Vending-Bench 2 | 5,396 | — |

## Reasoning

- Gemini 3.5 Flash: 62.8 (#18)
- Gemini 3.7 Flash: 70.0 (#15)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| ARC-AGI-2 | 72.1% | 84.6% |
| NYT Connections (extended) | 92.6% | 94% |
| ARC-AGI-1 | 92.5% | 95.5% |
| CritPt | 13.1% | 14.3% |
| Chess Puzzles | 50% | 47% |
| LMArena Hard Prompts | 1488 | 1494 |
| Mystery Game Puzzles | 32% | 37% |
| DTBench | 94.7% | 96.8% |
| LMCA | 47.1% | 50.4% |
| Epoch Capabilities Index | 154.46 | 157.27 |
| SimpleBench | 76.7% | — |
| EnigmaEval | 25.4% | — |
| EBR-Bench | 4.8% | — |
| Surface Evolver Bench | 58.1% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.5 Flash: 60.7 (#36)
- Gemini 3.7 Flash: 69.6 (#23)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 62.8% | 71.6% |
| FrontierMath Tier 4 | 26.8% | 36.6% |
| OTIS Mock AIME 2024-2025 | 95.6% | 97.2% |
| ProofBench | 31% | 58% |
| LMArena Math | 1504 | 1507 |
| MathArena Final-Answer Competitions | 76.3% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Gemini 3.5 Flash: 66.3 (#11)
- Gemini 3.7 Flash: 69.7 (#5)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 92.8% | 94.8% |
| SimpleQA Verified | 66.2% | 69.2% |
| LMArena Expert | 1495 | 1508 |

## Multimodal

- Gemini 3.5 Flash: 45.7 (#15)
- Gemini 3.7 Flash: 37.3 (#73)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1310 | 1316 |
| Blueprint-Bench 2 | 33.6% | — |
| Furniture Assembly | — | 26.7% |
| LMArena Document | 1463 | — |

## Multilingual

- Gemini 3.5 Flash: 57.0 (#13)
- Gemini 3.7 Flash: 57.6 (#7)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1476 | 1484 |
| LMArena Chinese | 1526 | 1548 |
| LMArena French | 1490 | 1505 |
| LMArena German | 1492 | 1498 |
| LMArena Japanese | 1486 | 1512 |
| LMArena Korean | 1451 | 1483 |
| LMArena Russian | 1493 | 1516 |
| LMArena Spanish | 1480 | 1503 |

## Instruction Following

- Gemini 3.5 Flash: 77.0 (#30)
- Gemini 3.7 Flash: 77.7 (#15)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1467 | 1483 |

## Long Context

- Gemini 3.5 Flash: 45.4 (#38)
- Gemini 3.7 Flash: 45.7 (#30)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1482 | 1492 |

## Writing & Preference

- Gemini 3.5 Flash: 65.5 (#47)
- Gemini 3.7 Flash: 71.2 (#20)

| Benchmark | Gemini 3.5 Flash | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1482 | 1486 |
| LMArena Creative Writing | 1470 | 1490 |
| LMArena Multi-Turn | 1481 | 1489 |
| EQ-Bench Creative Writing | — | 1723 |
| EQ-Bench 4 | 1087 | — |

## FAQ

### Is Gemini 3.5 Flash better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 54.2 on the Noometry Index.

### Which is cheaper, Gemini 3.5 Flash 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; Gemini 3.5 Flash lists at $1.50 and $9.

### Is Gemini 3.5 Flash or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 49.4 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1.05M tokens.

### How many benchmarks do Gemini 3.5 Flash and Gemini 3.7 Flash share?

39 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Gemini 3.7 Flash has 44.