# Gemma 1.1 2b IT vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-1-1-2b-it-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Gemma 1.1 2b IT scores higher in 0 categories and Inkling in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.5 to 25.3.

## Snapshot

| | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 28.8 | 44.1 |
| Rank | 313 | 75 |
| Context | — | 66K |
| Input $/M | — | $1.87 |
| Output $/M | — | $4.68 |
| Weights | Open | Open |

## Coding

- Gemma 1.1 2b IT: 29.6 (#294)
- Inkling: 34.1 (#229)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Coding | 1034 | 1463 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
| HumanEval+ | 17.7% | — |
| MBPP+ | 23.3% | — |

## Agentic & Tool Use

- Gemma 1.1 2b IT: —
- Inkling: 29.5 (#76)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- Gemma 1.1 2b IT: 18.2 (#268)
- Inkling: 40.6 (#48)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1452 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.6 |

## Math

- Gemma 1.1 2b IT: 28.3 (#230)
- Inkling: 31.2 (#198)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Math | 1047 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |

## Knowledge

- Gemma 1.1 2b IT: 26.0 (#255)
- Inkling: 55.2 (#44)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Expert | 970 | 1468 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |

## Multilingual

- Gemma 1.1 2b IT: 24.7 (#284)
- Inkling: 54.2 (#49)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Non-English | 988 | 1434 |
| LMArena Chinese | 1011 | 1495 |
| LMArena German | 944 | 1456 |
| LMArena Korean | 899 | 1401 |
| LMArena Russian | 990 | 1430 |
| LMArena French | — | 1453 |
| LMArena Japanese | — | 1428 |
| LMArena Spanish | — | 1442 |

## Instruction Following

- Gemma 1.1 2b IT: 50.1 (#294)
- Inkling: 75.3 (#65)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Instruction Following | 992 | 1427 |

## Long Context

- Gemma 1.1 2b IT: 30.5 (#281)
- Inkling: 43.9 (#79)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Longer Query | 1003 | 1436 |

## Writing & Preference

- Gemma 1.1 2b IT: 25.3 (#301)
- Inkling: 65.5 (#48)

| Benchmark | Gemma 1.1 2b IT | Inkling |
|---|---|---|
| LMArena Text | 1022 | 1443 |
| LMArena Creative Writing | 998 | 1390 |
| LMArena Multi-Turn | 958 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Gemma 1.1 2b IT better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 28.8 on the Noometry Index.

### Is Gemma 1.1 2b IT or Inkling better for coding?

Inkling scores higher on coding benchmarks: 34.1 versus 29.6 in the Noometry coding category.

### How many benchmarks do Gemma 1.1 2b IT and Inkling share?

14 benchmarks have published results for both models. Gemma 1.1 2b IT has 16 scored results on Noometry and Inkling has 41.