# Gemma 3 27B vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 30.8 on the Noometry Index. Gemma 3 27B costs 6.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-27b-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Inkling-Small in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.2 to 25.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 90% for Inkling-Small.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 131K.

## Snapshot

| | Gemma 3 27B | Inkling-Small |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 30.8 | 46.5 |
| Rank | 284 | 63 |
| Context | 131K | 524K |
| Input $/M | $0.08 | $0.45 |
| Output $/M | $0.16 | $1.20 |
| Weights | Open | Open |

## Coding

- Gemma 3 27B: 22.5 (#334)
- Inkling-Small: 43.6 (#85)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| SciCode | 21.2% | 48.7% |
| LMArena Coding | 1322 | 1451 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1409 |
| LiveBench Coding | 39.9% | — |

## Agentic & Tool Use

- Gemma 3 27B: 25.1 (#110)
- Inkling-Small: —

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |

## Reasoning

- Gemma 3 27B: 16.7 (#301)
- Inkling-Small: 38.6 (#63)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| CritPt | 0% | 8.3% |
| Chess Puzzles | 0% | 18% |
| LMArena Hard Prompts | 1340 | 1423 |
| Epoch Capabilities Index | 130.04 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| Kagi LLM Benchmark | 40.4% | — |
| ARC-AGI-1 | — | 84% |
| LiveBench Reasoning | 43.8% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| LiveBench | 50% | — |

## Math

- Gemma 3 27B: 25.9 (#265)
- Inkling-Small: 45.1 (#77)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 90% |
| LMArena Math | 1312 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |

## Knowledge

- Gemma 3 27B: 25.5 (#261)
- Inkling-Small: 48.2 (#77)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| GPQA Diamond | 47.7% | 88.5% |
| LMArena Expert | 1304 | 1442 |
| SimpleQA Verified | — | 19.1% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 3 27B: 32.6 (#100)
- Inkling-Small: 39.1 (#62)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| LMArena Vision | 1164 | 1235 |
| GeoBench | 52% | — |

## Multilingual

- Gemma 3 27B: 46.9 (#155)
- Inkling-Small: 51.7 (#104)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1334 | 1402 |
| LMArena Chinese | 1346 | 1465 |
| LMArena French | 1368 | 1436 |
| LMArena German | 1362 | 1405 |
| LMArena Japanese | 1287 | 1405 |
| LMArena Korean | 1308 | 1363 |
| LMArena Russian | 1349 | 1391 |
| LMArena Spanish | 1349 | 1428 |

## Instruction Following

- Gemma 3 27B: 70.6 (#160)
- Inkling-Small: 73.8 (#114)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1321 | 1399 |
| LiveBench Instruction Following | 74.9% | — |

## Long Context

- Gemma 3 27B: 27.6 (#293)
- Inkling-Small: 42.7 (#118)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1333 | 1401 |
| Fiction.LiveBench | 33.3% | — |

## Writing & Preference

- Gemma 3 27B: 52.5 (#168)
- Inkling-Small: 59.6 (#107)

| Benchmark | Gemma 3 27B | Inkling-Small |
|---|---|---|
| LMArena Text | 1358 | 1414 |
| LMArena Creative Writing | 1346 | 1331 |
| EQ-Bench Creative Writing | 1266 | 1491 |
| LMArena Multi-Turn | 1345 | 1418 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |

## FAQ

### Is Gemma 3 27B better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 30.8 on the Noometry Index. Gemma 3 27B costs 6.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 27B or Inkling-Small?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Gemma 3 27B or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 22.5 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 131K.

### How many benchmarks do Gemma 3 27B and Inkling-Small share?

25 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Inkling-Small has 33.