# Granite 4.0 H Small vs Yi-Lightning

> Granite 4.0 H Small and Yi-Lightning score almost the same on the Noometry Index (35.9 vs 36.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-yi-lightning
- 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 2 categories and Yi-Lightning in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Granite 4.0 H Small leads 35.8 to 27.0.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| Provider | IBM | 01.AI |
| Noometry Index | 35.9 | 36.5 |
| Rank | 213 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Yi-Lightning: 27.0 (#315)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1247 | 1313 |
| Aider Polyglot | — | 12.9% |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Yi-Lightning: 24.9 (#137)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1302 |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Yi-Lightning: 33.5 (#173)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Math | 1251 | 1300 |
| Omni-MATH | 29.6% | — |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Yi-Lightning: 34.8 (#182)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1244 | 1286 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Yi-Lightning: 42.4 (#191)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1216 | 1269 |
| LMArena Chinese | 1250 | 1320 |
| LMArena Russian | 1198 | 1255 |
| LMArena Spanish | 1258 | 1315 |
| LMArena French | — | 1304 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Yi-Lightning: 67.6 (#191)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1221 | 1278 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Yi-Lightning: 39.4 (#176)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1240 | 1297 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Yi-Lightning: 50.4 (#178)

| Benchmark | Granite 4.0 H Small | Yi-Lightning |
|---|---|---|
| LMArena Text | 1241 | 1302 |
| LMArena Creative Writing | 1210 | 1280 |
| LMArena Multi-Turn | 1243 | 1311 |
| WildBench | 73.9% | — |

## FAQ

### Is Granite 4.0 H Small better than Yi-Lightning?

Granite 4.0 H Small and Yi-Lightning score almost the same on the Noometry Index (35.9 vs 36.5), so choose on price, context window or the category you care about most.

### Is Granite 4.0 H Small or Yi-Lightning better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 27.0 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Yi-Lightning share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Yi-Lightning has 18.