# Gemma 3 1B vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 20.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-1b-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Gemma 3 1B scores higher in 0 categories and Inkling in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for Gemma 3 1B and 88.9% for Inkling.

## Snapshot

| | Gemma 3 1B | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 20.7 | 44.1 |
| Rank | 348 | 75 |
| Context | — | 66K |
| Input $/M | — | $1.87 |
| Output $/M | — | $4.68 |
| Weights | Open | Open |

## Coding

- Gemma 3 1B: —
- Inkling: 34.1 (#229)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| LMArena Coding | — | 1463 |
| ALE-Bench | — | 946 |

## Agentic & Tool Use

- Gemma 3 1B: 13.5 (#144)
- Inkling: 29.5 (#76)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| Berkeley Function Calling Leaderboard | 7.2% | — |
| τ²-bench Banking | — | 25% |

## Reasoning

- Gemma 3 1B: 18.5 (#260)
- Inkling: 40.6 (#48)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| LMArena Hard Prompts | — | 1452 |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.6 |

## Math

- Gemma 3 1B: 9.6 (#310)
- Inkling: 31.2 (#198)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 88.9% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |
| LMArena Math | — | 1482 |

## Knowledge

- Gemma 3 1B: 7.1 (#309)
- Inkling: 55.2 (#44)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| GPQA Diamond | 19.9% | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1468 |

## Multilingual

- Gemma 3 1B: —
- Inkling: 54.2 (#49)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| LMArena Non-English | — | 1434 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1453 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1428 |
| LMArena Korean | — | 1401 |
| LMArena Russian | — | 1430 |
| LMArena Spanish | — | 1442 |

## Instruction Following

- Gemma 3 1B: —
- Inkling: 75.3 (#65)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| LMArena Instruction Following | — | 1427 |

## Long Context

- Gemma 3 1B: —
- Inkling: 43.9 (#79)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| LMArena Longer Query | — | 1436 |

## Writing & Preference

- Gemma 3 1B: —
- Inkling: 65.5 (#48)

| Benchmark | Gemma 3 1B | Inkling |
|---|---|---|
| LMArena Text | — | 1443 |
| LMArena Creative Writing | — | 1390 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
| LMArena Multi-Turn | — | 1436 |

## FAQ

### Is Gemma 3 1B better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 20.7 on the Noometry Index.

### How many benchmarks do Gemma 3 1B and Inkling share?

3 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and Inkling has 41.