# GPT-4 Turbo vs Granite 4.0 H Small

> Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-vs-ibm-granite-h-small
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. GPT-4 Turbo scores higher in 3 categories and Granite 4.0 H Small in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.0 H Small leads 31.4 to 9.0.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 30.5 | 36.5 |
| Rank | 292 | 214 |
| Context | 128K | — |
| Input $/M | $10 | — |
| Output $/M | $30 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4 Turbo: 33.8 (#249)
- Granite 4.0 H Small: 36.4 (#209)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1268 | 1249 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- Granite 4.0 H Small: —

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| METR Time Horizons | 36.7% | — |

## Reasoning

- GPT-4 Turbo: 15.3 (#317)
- Granite 4.0 H Small: 24.4 (#163)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1240 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |

## Math

- GPT-4 Turbo: 9.0 (#322)
- Granite 4.0 H Small: 31.4 (#223)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1272 | 1247 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| Omni-MATH | — | 29.6% |
| MATH Level 5 | 46.7% | — |

## Knowledge

- GPT-4 Turbo: 24.3 (#268)
- Granite 4.0 H Small: 32.0 (#215)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1223 | 1251 |
| GPQA Diamond | 46.6% | — |
| MMLU-Pro | — | 56.9% |
| Confabulations | 28.4% | — |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.6 (#110)
- Granite 4.0 H Small: —

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Vision | 1090 | — |

## Multilingual

- GPT-4 Turbo: 40.5 (#216)
- Granite 4.0 H Small: 38.6 (#228)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1245 | 1216 |
| LMArena Chinese | 1242 | 1249 |
| LMArena Russian | 1259 | 1201 |
| LMArena Spanish | 1260 | 1258 |
| LMArena French | 1276 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |

## Instruction Following

- GPT-4 Turbo: 65.8 (#216)
- Granite 4.0 H Small: 68.7 (#183)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1249 | 1222 |
| IFEval | — | 89% |

## Long Context

- GPT-4 Turbo: 38.0 (#206)
- Granite 4.0 H Small: 37.7 (#213)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1254 | 1242 |

## Writing & Preference

- GPT-4 Turbo: 47.7 (#206)
- Granite 4.0 H Small: 43.8 (#227)

| Benchmark | GPT-4 Turbo | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1272 | 1241 |
| LMArena Creative Writing | 1269 | 1211 |
| LMArena Multi-Turn | 1267 | 1242 |
| WildBench | — | 73.9% |

## FAQ

### Is GPT-4 Turbo better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 30.5 on the Noometry Index.

### Is GPT-4 Turbo or Granite 4.0 H Small better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 33.8 in the Noometry coding category.

### How many benchmarks do GPT-4 Turbo and Granite 4.0 H Small share?

13 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Granite 4.0 H Small has 19.