# Gemini 3.5 Flash Lite vs Step 3

> Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.8 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-lite-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 8 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.0 to 36.2.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 41.8 | 39.9 |
| Rank | 113 | 145 |
| Context | 1.05M | — |
| Input $/M | $0.30 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.5 Flash Lite: 42.1 (#96)
- Step 3: 39.5 (#144)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Coding | 1455 | 1367 |
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| WeirdML | 39% | — |
| ALE-Bench | 765.27 | — |

## Agentic & Tool Use

- Gemini 3.5 Flash Lite: 28.6 (#82)
- Step 3: —

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| GDP.pdf | 10% | — |

## Reasoning

- Gemini 3.5 Flash Lite: 27.8 (#95)
- Step 3: 27.6 (#102)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1441 | 1355 |
| ARC-AGI-2 | 10.3% | — |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 60.4% | — |
| ARC-AGI-1 | 53.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 22% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 145.12 | — |

## Math

- Gemini 3.5 Flash Lite: 25.7 (#245)
- Step 3: 34.9 (#148)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Math | 1431 | 1366 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 13% | — |

## Knowledge

- Gemini 3.5 Flash Lite: 50.0 (#66)
- Step 3: 36.2 (#161)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Expert | 1430 | 1333 |
| GPQA Diamond | 83.3% | — |

## Multimodal

- Gemini 3.5 Flash Lite: 40.3 (#38)
- Step 3: 34.9 (#81)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Vision | 1266 | 1176 |

## Multilingual

- Gemini 3.5 Flash Lite: 53.8 (#59)
- Step 3: 46.5 (#154)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Non-English | 1428 | 1327 |
| LMArena Chinese | 1467 | 1396 |
| LMArena German | 1454 | 1371 |
| LMArena Korean | 1406 | 1271 |
| LMArena Russian | 1443 | 1331 |
| LMArena Spanish | 1440 | 1372 |
| LMArena French | 1452 | — |
| LMArena Japanese | 1428 | — |

## Instruction Following

- Gemini 3.5 Flash Lite: 75.0 (#77)
- Step 3: 70.6 (#159)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1332 |

## Long Context

- Gemini 3.5 Flash Lite: 43.8 (#80)
- Step 3: 40.3 (#152)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Longer Query | 1435 | 1326 |

## Writing & Preference

- Gemini 3.5 Flash Lite: 64.4 (#55)
- Step 3: 54.5 (#146)

| Benchmark | Gemini 3.5 Flash Lite | Step 3 |
|---|---|---|
| LMArena Text | 1436 | 1351 |
| LMArena Creative Writing | 1419 | 1322 |
| LMArena Multi-Turn | 1445 | 1340 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is Gemini 3.5 Flash Lite better than Step 3?

Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.8 to 39.9 on the Noometry Index.

### Is Gemini 3.5 Flash Lite or Step 3 better for coding?

Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.1 versus 39.5 in the Noometry coding category.

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

16 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 38 scored results on Noometry and Step 3 has 17.
