# Granite 4.0 H Small vs Olmo 3 32b Think

> Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-olmo-3-32b-think
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 4.0 H Small scores higher in 1 category and Olmo 3 32b Think in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3 32b Think leads 49.1 to 43.8.

## Snapshot

| | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 36.5 | 38.7 |
| Rank | 214 | 183 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 36.4 (#209)
- Olmo 3 32b Think: 38.6 (#172)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1249 | 1319 |

## Reasoning

- Granite 4.0 H Small: 24.4 (#163)
- Olmo 3 32b Think: 25.9 (#140)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1302 |

## Math

- Granite 4.0 H Small: 31.4 (#223)
- Olmo 3 32b Think: 36.5 (#165)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1247 | 1316 |
| Omni-MATH | 29.6% | — |

## Knowledge

- Granite 4.0 H Small: 32.0 (#215)
- Olmo 3 32b Think: 35.0 (#190)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1251 | 1273 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |

## Multilingual

- Granite 4.0 H Small: 38.6 (#228)
- Olmo 3 32b Think: 41.2 (#210)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1216 | 1255 |
| LMArena Chinese | 1249 | 1300 |
| LMArena Russian | 1201 | 1254 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
| LMArena Spanish | 1258 | — |

## Instruction Following

- Granite 4.0 H Small: 68.7 (#183)
- Olmo 3 32b Think: 67.2 (#198)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1222 | 1275 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.7 (#213)
- Olmo 3 32b Think: 39.4 (#182)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1242 | 1296 |

## Writing & Preference

- Granite 4.0 H Small: 43.8 (#227)
- Olmo 3 32b Think: 49.1 (#193)

| Benchmark | Granite 4.0 H Small | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1241 | 1300 |
| LMArena Creative Writing | 1211 | 1256 |
| LMArena Multi-Turn | 1242 | 1290 |
| WildBench | 73.9% | — |

## FAQ

### Is Granite 4.0 H Small better than Olmo 3 32b Think?

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 36.5 on the Noometry Index.

### Is Granite 4.0 H Small or Olmo 3 32b Think better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 36.4 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Olmo 3 32b Think share?

12 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Olmo 3 32b Think has 14.