# Granite 4.0 H Small vs Mercury

> Mercury is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-mercury
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Granite 4.0 H Small scores higher in 2 categories and Mercury in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.0 H Small leads 23.4 to 16.8.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 H Small | Mercury |
|---|---|---|
| Provider | IBM | Inception |
| Noometry Index | 35.9 | 37.3 |
| Rank | 213 | 192 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Mercury: 38.1 (#164)

| Benchmark | Granite 4.0 H Small | Mercury |
|---|---|---|
| LMArena Coding | 1247 | 1323 |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Mercury: 16.8 (#288)

| Benchmark | Granite 4.0 H Small | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1284 |
| Kagi LLM Benchmark | — | 21.6% |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Mercury: —

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

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Mercury: —

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

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Mercury: 41.7 (#201)

| Benchmark | Granite 4.0 H Small | Mercury |
|---|---|---|
| LMArena Non-English | 1216 | 1259 |
| LMArena Chinese | 1250 | — |
| LMArena Russian | 1198 | — |
| LMArena Spanish | 1258 | — |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Mercury: 65.3 (#220)

| Benchmark | Granite 4.0 H Small | Mercury |
|---|---|---|
| LMArena Instruction Following | 1221 | 1238 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Mercury: 38.3 (#193)

| Benchmark | Granite 4.0 H Small | Mercury |
|---|---|---|
| LMArena Longer Query | 1240 | 1264 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Mercury: 46.2 (#216)

| Benchmark | Granite 4.0 H Small | Mercury |
|---|---|---|
| LMArena Text | 1241 | 1282 |
| LMArena Creative Writing | 1210 | 1186 |
| LMArena Multi-Turn | 1243 | 1283 |
| WildBench | 73.9% | — |

## FAQ

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

Mercury is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.

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

Mercury scores higher on coding benchmarks: 38.1 versus 35.8 in the Noometry coding category.

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

8 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Mercury has 9.