# Hy3 vs Granite 4.0 H Small

> Hy3 is the stronger model overall, scoring 43.6 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy3-vs-ibm-granite-h-small
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Hy3 scores higher in 8 categories and Granite 4.0 H Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 44.0.

## Snapshot

| | Hy3 | Granite 4.0 H Small |
|---|---|---|
| Provider | Tencent | IBM |
| Noometry Index | 43.6 | 35.9 |
| Rank | 79 | 213 |
| Context | 262K | — |
| Input $/M | $0.13 | — |
| Output $/M | $0.53 | — |
| Weights | Open | Open |

## Coding

- Hy3: 46.6 (#60)
- Granite 4.0 H Small: 35.8 (#207)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1465 | 1247 |
| LMArena WebDev | 1509 | — |

## Reasoning

- Hy3: 25.0 (#134)
- Granite 4.0 H Small: 23.4 (#164)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1240 |
| NYT Connections (extended) | 41.2% | — |

## Math

- Hy3: 37.4 (#98)
- Granite 4.0 H Small: 29.3 (#219)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1475 | 1251 |
| Omni-MATH | — | 29.6% |

## Knowledge

- Hy3: 40.2 (#108)
- Granite 4.0 H Small: 31.5 (#210)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1461 | 1244 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |

## Multilingual

- Hy3: 53.7 (#60)
- Granite 4.0 H Small: 38.7 (#223)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1427 | 1216 |
| LMArena Chinese | 1496 | 1250 |
| LMArena Russian | 1435 | 1198 |
| LMArena Spanish | 1448 | 1258 |
| LMArena French | 1461 | — |
| LMArena Korean | 1390 | — |

## Instruction Following

- Hy3: 75.3 (#68)
- Granite 4.0 H Small: 68.9 (#178)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1425 | 1221 |
| IFEval | — | 89% |

## Long Context

- Hy3: 44.1 (#70)
- Granite 4.0 H Small: 37.6 (#209)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1443 | 1240 |

## Writing & Preference

- Hy3: 62.5 (#75)
- Granite 4.0 H Small: 44.0 (#222)

| Benchmark | Hy3 | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1442 | 1241 |
| LMArena Creative Writing | 1399 | 1210 |
| LMArena Multi-Turn | 1436 | 1243 |
| WildBench | — | 73.9% |

## FAQ

### Is Hy3 better than Granite 4.0 H Small?

Hy3 is the stronger model overall, scoring 43.6 to 35.9 on the Noometry Index.

### Is Hy3 or Granite 4.0 H Small better for coding?

Hy3 scores higher on coding benchmarks: 46.6 versus 35.8 in the Noometry coding category.

### How many benchmarks do Hy3 and Granite 4.0 H Small share?

13 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Granite 4.0 H Small has 19.