# Gemini 3.6 Flash vs Inkling-Small

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 46.5 on the Noometry Index. Inkling-Small costs 2.4× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 8 categories and Inkling-Small in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 38.6.
- The biggest single-benchmark swing is SimpleQA Verified: 66.2% for Gemini 3.6 Flash and 19.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 54.1 | 46.5 |
| Rank | 33 | 63 |
| Context | 1.05M | 524K |
| Input $/M | $0.75 | $0.45 |
| Output $/M | $3.75 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- Inkling-Small: 43.6 (#85)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1538 | 1409 |
| SciCode | 52.7% | 48.7% |
| LMArena Coding | 1491 | 1451 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| WeirdML | 56.1% | — |
| ALE-Bench | 715.52 | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- Inkling-Small: —

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| APEX-Agents | 46.9% | — |
| GDP.pdf | 14% | — |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- Inkling-Small: 38.6 (#63)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 60.4% | 40.1% |
| ARC-AGI-1 | 91.2% | 84% |
| CritPt | 10.6% | 8.3% |
| Chess Puzzles | 43% | 18% |
| LMArena Hard Prompts | 1485 | 1423 |
| Mystery Game Puzzles | 30% | 6% |
| Epoch Capabilities Index | 154.25 | 150.15 |
| NYT Connections (extended) | 89% | — |
| DTBench | 95.5% | — |
| LMCA | 44.9% | — |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- Inkling-Small: 45.1 (#77)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 46.3% |
| FrontierMath Tier 4 | 22% | 17.1% |
| OTIS Mock AIME 2024-2025 | 94.2% | 90% |
| ProofBench | 36% | 6% |
| LMArena Math | 1505 | 1459 |
| MathArena Final-Answer Competitions | 70.8% | — |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- Inkling-Small: 48.2 (#77)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| GPQA Diamond | 94.1% | 88.5% |
| SimpleQA Verified | 66.2% | 19.1% |
| LMArena Expert | 1488 | 1442 |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- Inkling-Small: 39.1 (#62)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| LMArena Vision | 1298 | 1235 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- Inkling-Small: 51.7 (#104)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1469 | 1402 |
| LMArena Chinese | 1531 | 1465 |
| LMArena French | 1504 | 1436 |
| LMArena German | 1478 | 1405 |
| LMArena Japanese | 1476 | 1405 |
| LMArena Korean | 1431 | 1363 |
| LMArena Russian | 1487 | 1391 |
| LMArena Spanish | 1475 | 1428 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- Inkling-Small: 73.8 (#114)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1466 | 1399 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- Inkling-Small: 42.7 (#118)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1474 | 1401 |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- Inkling-Small: 59.6 (#107)

| Benchmark | Gemini 3.6 Flash | Inkling-Small |
|---|---|---|
| LMArena Text | 1479 | 1414 |
| LMArena Creative Writing | 1465 | 1331 |
| EQ-Bench Creative Writing | 1604 | 1491 |
| LMArena Multi-Turn | 1481 | 1418 |

## FAQ

### Is Gemini 3.6 Flash better than Inkling-Small?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 46.5 on the Noometry Index. Inkling-Small costs 2.4× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.6 Flash or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 3.6 Flash or Inkling-Small better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 524K.

### How many benchmarks do Gemini 3.6 Flash and Inkling-Small share?

33 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Inkling-Small has 33.