# GPT-5.2 Pro vs Granite 4.0 H Small

> GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-pro-vs-ibm-granite-h-small
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 31.4.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 52.3 | 36.5 |
| Rank | 39 | 214 |
| Context | 400K | — |
| Input $/M | $21 | — |
| Output $/M | $168 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Pro: —
- Granite 4.0 H Small: 36.4 (#209)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | — | 1249 |

## Reasoning

- GPT-5.2 Pro: 51.5 (#33)
- Granite 4.0 H Small: 24.4 (#163)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1240 |
| Epoch Capabilities Index | 155.4 | — |

## Math

- GPT-5.2 Pro: 65.3 (#29)
- Granite 4.0 H Small: 31.4 (#223)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1247 |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- GPT-5.2 Pro: —
- Granite 4.0 H Small: 32.0 (#215)

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

## Multilingual

- GPT-5.2 Pro: —
- Granite 4.0 H Small: 38.6 (#228)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | — | 1216 |
| LMArena Chinese | — | 1249 |
| LMArena Russian | — | 1201 |
| LMArena Spanish | — | 1258 |

## Instruction Following

- GPT-5.2 Pro: —
- Granite 4.0 H Small: 68.7 (#183)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| IFEval | — | 89% |
| LMArena Instruction Following | — | 1222 |

## Long Context

- GPT-5.2 Pro: —
- Granite 4.0 H Small: 37.7 (#213)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | — | 1242 |

## Writing & Preference

- GPT-5.2 Pro: —
- Granite 4.0 H Small: 43.8 (#227)

| Benchmark | GPT-5.2 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | — | 1241 |
| LMArena Creative Writing | — | 1211 |
| WildBench | — | 73.9% |
| LMArena Multi-Turn | — | 1242 |

## FAQ

### Is GPT-5.2 Pro better than Granite 4.0 H Small?

GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 36.5 on the Noometry Index.

### How many benchmarks do GPT-5.2 Pro and Granite 4.0 H Small share?

0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Granite 4.0 H Small has 19.