# Granite 4.0 H Small vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 1 category and Inkling in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 31.5.

## Snapshot

| | Granite 4.0 H Small | Inkling |
|---|---|---|
| Provider | IBM | Thinking Machines Lab |
| Noometry Index | 35.9 | 44.1 |
| Rank | 213 | 75 |
| Context | — | 66K |
| Input $/M | — | $1.87 |
| Output $/M | — | $4.68 |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Inkling: 34.1 (#229)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Coding | 1247 | 1463 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |

## Agentic & Tool Use

- Granite 4.0 H Small: —
- Inkling: 29.5 (#76)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Inkling: 40.6 (#48)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1240 | 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

- Granite 4.0 H Small: 29.3 (#219)
- Inkling: 31.2 (#198)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Math | 1251 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| Omni-MATH | 29.6% | — |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Inkling: 55.2 (#44)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Expert | 1244 | 1468 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Inkling: 54.2 (#49)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Non-English | 1216 | 1434 |
| LMArena Chinese | 1250 | 1495 |
| LMArena Russian | 1198 | 1430 |
| LMArena Spanish | 1258 | 1442 |
| LMArena French | — | 1453 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1428 |
| LMArena Korean | — | 1401 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Inkling: 75.3 (#65)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Instruction Following | 1221 | 1427 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Inkling: 43.9 (#79)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Longer Query | 1240 | 1436 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Inkling: 65.5 (#48)

| Benchmark | Granite 4.0 H Small | Inkling |
|---|---|---|
| LMArena Text | 1241 | 1443 |
| LMArena Creative Writing | 1210 | 1390 |
| LMArena Multi-Turn | 1243 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| WildBench | 73.9% | — |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Granite 4.0 H Small better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 35.9 on the Noometry Index.

### Is Granite 4.0 H Small or Inkling better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 34.1 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Inkling share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Inkling has 41.