# Claude 2 vs Granite 4.0 H Small

> Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-ibm-granite-h-small
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Granite 4.0 H Small leads 29.3 to 8.7.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| Provider | Anthropic | IBM |
| Noometry Index | 24.7 | 35.9 |
| Rank | 342 | 213 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Granite 4.0 H Small: 35.8 (#207)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | — | 1247 |
| HumanEval+ | 61.6% | — |

## Reasoning

- Claude 2: 20.8 (#213)
- Granite 4.0 H Small: 23.4 (#164)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | — | 1240 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.08 | — |

## Math

- Claude 2: 8.7 (#314)
- Granite 4.0 H Small: 29.3 (#219)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1251 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 17.0 (#282)
- Granite 4.0 H Small: 31.5 (#210)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
| LMArena Expert | — | 1244 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multilingual

- Claude 2: —
- Granite 4.0 H Small: 38.7 (#223)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | — | 1216 |
| LMArena Chinese | — | 1250 |
| LMArena Russian | — | 1198 |
| LMArena Spanish | — | 1258 |

## Instruction Following

- Claude 2: —
- Granite 4.0 H Small: 68.9 (#178)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| IFEval | — | 89% |
| LMArena Instruction Following | — | 1221 |

## Long Context

- Claude 2: —
- Granite 4.0 H Small: 37.6 (#209)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | — | 1240 |

## Writing & Preference

- Claude 2: —
- Granite 4.0 H Small: 44.0 (#222)

| Benchmark | Claude 2 | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | — | 1241 |
| LMArena Creative Writing | — | 1210 |
| WildBench | — | 73.9% |
| LMArena Multi-Turn | — | 1243 |

## FAQ

### Is Claude 2 better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and Granite 4.0 H Small share?

0 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Granite 4.0 H Small has 19.