# Granite 4.0 H Small vs Nova Premier 1.0

> Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-nova-premier-1-0
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Granite 4.0 H Small scores higher in 2 categories and Nova Premier 1.0 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nova Premier 1.0 leads 51.0 to 43.8.
- The biggest single-benchmark swing is MMLU-Pro: 56.9% for Granite 4.0 H Small and 72.6% for Nova Premier 1.0.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| Provider | IBM | Amazon |
| Noometry Index | 36.5 | 38.3 |
| Rank | 214 | 189 |
| Context | — | 1M |
| Input $/M | — | $2.50 |
| Output $/M | — | $12.50 |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 H Small: 36.4 (#209)
- Nova Premier 1.0: —

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Coding | 1249 | — |

## Reasoning

- Granite 4.0 H Small: 24.4 (#163)
- Nova Premier 1.0: 23.0 (#185)

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| LMArena Hard Prompts | 1240 | — |

## Math

- Granite 4.0 H Small: 31.4 (#223)
- Nova Premier 1.0: 33.8 (#199)

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | 29.6% | 35% |
| LMArena Math | 1247 | — |

## Knowledge

- Granite 4.0 H Small: 32.0 (#215)
- Nova Premier 1.0: 35.8 (#180)

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | 56.9% | 72.6% |
| GPQA (HELM) | 38.3% | 51.8% |
| Vectara Hallucination Rate | 5.2% | — |
| LMArena Expert | 1251 | — |

## Multilingual

- Granite 4.0 H Small: 38.6 (#228)
- Nova Premier 1.0: —

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1249 | — |
| LMArena Russian | 1201 | — |
| LMArena Spanish | 1258 | — |

## Instruction Following

- Granite 4.0 H Small: 68.7 (#183)
- Nova Premier 1.0: 66.8 (#204)

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| IFEval | 89% | 80.3% |
| LMArena Instruction Following | 1222 | — |

## Long Context

- Granite 4.0 H Small: 37.7 (#213)
- Nova Premier 1.0: —

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1242 | — |

## Writing & Preference

- Granite 4.0 H Small: 43.8 (#227)
- Nova Premier 1.0: 51.0 (#178)

| Benchmark | Granite 4.0 H Small | Nova Premier 1.0 |
|---|---|---|
| WildBench | 73.9% | 78.8% |
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1211 | — |
| LMArena Multi-Turn | 1242 | — |

## FAQ

### Is Granite 4.0 H Small better than Nova Premier 1.0?

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 36.5 on the Noometry Index.

### How many benchmarks do Granite 4.0 H Small and Nova Premier 1.0 share?

5 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Nova Premier 1.0 has 6.