# Gemini 3.5 Flash Lite vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 41.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-lite-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 6 categories and Inkling-Small in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 25.9.
- The biggest single-benchmark swing is ARC-AGI-1: 53.5% for Gemini 3.5 Flash Lite and 84% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.30 / $2.50 for Gemini 3.5 Flash Lite.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 41.5 | 46.5 |
| Rank | 133 | 63 |
| Context | 1.05M | 524K |
| Input $/M | $0.30 | $0.45 |
| Output $/M | $2.50 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.5 Flash Lite: 42.4 (#104)
- Inkling-Small: 43.6 (#85)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1440 | 1409 |
| SciCode | 41.3% | 48.7% |
| LMArena Coding | 1453 | 1451 |
| WeirdML | 39% | — |
| ALE-Bench | 765.27 | — |

## Agentic & Tool Use

- Gemini 3.5 Flash Lite: 25.7 (#107)
- Inkling-Small: —

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| APEX-Agents | 29.3% | — |
| GDP.pdf | 10% | — |

## Reasoning

- Gemini 3.5 Flash Lite: 27.8 (#114)
- Inkling-Small: 38.6 (#63)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 10.3% | 40.1% |
| ARC-AGI-1 | 53.5% | 84% |
| CritPt | 0% | 8.3% |
| Chess Puzzles | 22% | 18% |
| LMArena Hard Prompts | 1441 | 1423 |
| Mystery Game Puzzles | 19% | 6% |
| Epoch Capabilities Index | 145.13 | 150.15 |
| NYT Connections (extended) | 60.4% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |

## Math

- Gemini 3.5 Flash Lite: 25.9 (#264)
- Inkling-Small: 45.1 (#77)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 46.3% |
| FrontierMath Tier 4 | 0% | 17.1% |
| OTIS Mock AIME 2024-2025 | 71.1% | 90% |
| ProofBench | 13% | 6% |
| LMArena Math | 1433 | 1459 |

## Knowledge

- Gemini 3.5 Flash Lite: 50.1 (#72)
- Inkling-Small: 48.2 (#77)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| GPQA Diamond | 83.3% | 88.5% |
| LMArena Expert | 1435 | 1442 |
| SimpleQA Verified | — | 19.1% |

## Multimodal

- Gemini 3.5 Flash Lite: 41.1 (#40)
- Inkling-Small: 39.1 (#62)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| LMArena Vision | 1268 | 1235 |

## Multilingual

- Gemini 3.5 Flash Lite: 53.5 (#63)
- Inkling-Small: 51.7 (#104)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1427 | 1402 |
| LMArena Chinese | 1469 | 1465 |
| LMArena French | 1451 | 1436 |
| LMArena German | 1454 | 1405 |
| LMArena Japanese | 1427 | 1405 |
| LMArena Korean | 1407 | 1363 |
| LMArena Russian | 1443 | 1391 |
| LMArena Spanish | 1442 | 1428 |

## Instruction Following

- Gemini 3.5 Flash Lite: 74.8 (#85)
- Inkling-Small: 73.8 (#114)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1420 | 1399 |

## Long Context

- Gemini 3.5 Flash Lite: 43.9 (#84)
- Inkling-Small: 42.7 (#118)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1435 | 1401 |

## Writing & Preference

- Gemini 3.5 Flash Lite: 64.2 (#57)
- Inkling-Small: 59.6 (#107)

| Benchmark | Gemini 3.5 Flash Lite | Inkling-Small |
|---|---|---|
| LMArena Text | 1435 | 1414 |
| LMArena Creative Writing | 1420 | 1331 |
| EQ-Bench Creative Writing | 1559 | 1491 |
| LMArena Multi-Turn | 1445 | 1418 |

## FAQ

### Is Gemini 3.5 Flash Lite better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 41.5 on the Noometry Index.

### Which is cheaper, Gemini 3.5 Flash Lite or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Gemini 3.5 Flash Lite lists at $0.30 and $2.50.

### Is Gemini 3.5 Flash Lite or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.5 Flash Lite does, with 1.05M tokens against 524K.

### How many benchmarks do Gemini 3.5 Flash Lite and Inkling-Small share?

32 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Inkling-Small has 33.