# Gemini 3.5 Flash Lite vs Gemini 3 Deep Think

> Gemini 3.5 Flash Lite has enough public results to be ranked (#133); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-lite-vs-gemini-3-deep-think
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 0 categories and Gemini 3 Deep Think in 1 category; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 27.8.
- The biggest single-benchmark swing is ARC-AGI-2: 10.3% for Gemini 3.5 Flash Lite and 84.6% for Gemini 3 Deep Think.

## Snapshot

| | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 41.5 | 58.3 |
| Rank | 133 | — |
| Context | 1.05M | — |
| Input $/M | $0.30 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.5 Flash Lite: 42.4 (#104)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| WeirdML | 39% | — |
| LMArena Coding | 1453 | — |
| ALE-Bench | 765.27 | — |

## Agentic & Tool Use

- Gemini 3.5 Flash Lite: 25.7 (#107)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| APEX-Agents | 29.3% | — |
| GDP.pdf | 10% | — |

## Reasoning

- Gemini 3.5 Flash Lite: 27.8 (#114)
- Gemini 3 Deep Think: 70.2 (#14)

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| ARC-AGI-2 | 10.3% | 84.6% |
| ARC-AGI-1 | 53.5% | 96% |
| CritPt | 0% | 25.7% |
| NYT Connections (extended) | 60.4% | — |
| Chess Puzzles | 22% | — |
| LMArena Hard Prompts | 1441 | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 145.13 | — |

## Math

- Gemini 3.5 Flash Lite: 25.9 (#264)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 13% | — |
| LMArena Math | 1433 | — |

## Knowledge

- Gemini 3.5 Flash Lite: 50.1 (#72)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| GPQA Diamond | 83.3% | — |
| LMArena Expert | 1435 | — |

## Multimodal

- Gemini 3.5 Flash Lite: 41.1 (#40)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| LMArena Vision | 1268 | — |

## Multilingual

- Gemini 3.5 Flash Lite: 53.5 (#63)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| LMArena Non-English | 1427 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1451 | — |
| LMArena German | 1454 | — |
| LMArena Japanese | 1427 | — |
| LMArena Korean | 1407 | — |
| LMArena Russian | 1443 | — |
| LMArena Spanish | 1442 | — |

## Instruction Following

- Gemini 3.5 Flash Lite: 74.8 (#85)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| LMArena Instruction Following | 1420 | — |

## Long Context

- Gemini 3.5 Flash Lite: 43.9 (#84)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| LMArena Longer Query | 1435 | — |

## Writing & Preference

- Gemini 3.5 Flash Lite: 64.2 (#57)
- Gemini 3 Deep Think: —

| Benchmark | Gemini 3.5 Flash Lite | Gemini 3 Deep Think |
|---|---|---|
| LMArena Text | 1435 | — |
| LMArena Creative Writing | 1420 | — |
| EQ-Bench Creative Writing | 1559 | — |
| LMArena Multi-Turn | 1445 | — |

## FAQ

### Is Gemini 3.5 Flash Lite better than Gemini 3 Deep Think?

Gemini 3.5 Flash Lite has enough public results to be ranked (#133); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

### How many benchmarks do Gemini 3.5 Flash Lite and Gemini 3 Deep Think share?

3 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Gemini 3 Deep Think has 3.