# Gemma 4 31B IT vs Inkling

> Gemma 4 31B IT and Inkling score almost the same on the Noometry Index (43.2 vs 44.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemma 4 31B IT scores higher in 4 categories and Inkling in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 37.9.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 40.3% for Inkling.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Gemma 4 31B IT accepts more context: 262K tokens versus 66K.

## Snapshot

| | Gemma 4 31B IT | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 43.2 | 44.1 |
| Rank | 85 | 75 |
| Context | 262K | 66K |
| Input $/M | $0.09 | $1.87 |
| Output $/M | $0.34 | $4.68 |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 41.9 (#98)
- Inkling: 34.1 (#229)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| LMArena WebDev | 1364 | 1412 |
| SciCode | 43.4% | 47% |
| WeirdML | 52.3% | 32.3% |
| LMArena Coding | 1459 | 1463 |
| ALE-Bench | 925.5 | 946 |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |

## Agentic & Tool Use

- Gemma 4 31B IT: —
- Inkling: 29.5 (#76)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- Gemma 4 31B IT: 26.4 (#119)
- Inkling: 40.6 (#48)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| CritPt | 1.4% | 5.4% |
| Chess Puzzles | 5% | 21% |
| LMArena Hard Prompts | 1448 | 1452 |
| DTBench | 82.7% | 87.5% |
| LMCA | 39.3% | 37.6% |
| Epoch Capabilities Index | 142.74 | 148.6 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| ARC-AGI-1 | — | 79.5% |
| Thematic Generalization | 53% | — |
| Surface Evolver Bench | 30.6% | — |

## Math

- Gemma 4 31B IT: 41.3 (#72)
- Inkling: 31.2 (#198)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 88.9% |
| LMArena Math | 1464 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |

## Knowledge

- Gemma 4 31B IT: 37.9 (#141)
- Inkling: 55.2 (#44)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| GPQA Diamond | 75.8% | 88.3% |
| SimpleQA Verified | 10.4% | 40.3% |
| LMArena Expert | 1465 | 1468 |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 4 31B IT: 41.0 (#32)
- Inkling: —

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 54.0 (#52)
- Inkling: 54.2 (#49)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| LMArena Non-English | 1431 | 1434 |
| LMArena Chinese | 1478 | 1495 |
| LMArena French | 1436 | 1453 |
| LMArena Russian | 1462 | 1430 |
| LMArena Spanish | 1443 | 1442 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1428 |
| LMArena Korean | — | 1401 |

## Instruction Following

- Gemma 4 31B IT: 75.6 (#58)
- Inkling: 75.3 (#65)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| LMArena Instruction Following | 1433 | 1427 |

## Long Context

- Gemma 4 31B IT: 44.2 (#67)
- Inkling: 43.9 (#79)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| LMArena Longer Query | 1446 | 1436 |

## Writing & Preference

- Gemma 4 31B IT: 60.7 (#92)
- Inkling: 65.5 (#48)

| Benchmark | Gemma 4 31B IT | Inkling |
|---|---|---|
| LMArena Text | 1443 | 1443 |
| LMArena Creative Writing | 1416 | 1390 |
| EQ-Bench Creative Writing | 1368 | 1611 |
| EQ-Bench 4 | 1120 | 1226 |
| LMArena Multi-Turn | 1452 | 1436 |

## FAQ

### Is Gemma 4 31B IT better than Inkling?

Gemma 4 31B IT and Inkling score almost the same on the Noometry Index (43.2 vs 44.1), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 4 31B IT or Inkling?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Gemma 4 31B IT or Inkling better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 66K.

### How many benchmarks do Gemma 4 31B IT and Inkling share?

28 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Inkling has 41.