# GPT-4 vs Granite 4.2 30b

> Granite 4.2 30b is the stronger model overall, scoring 41.8 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-granite-4-2-30b
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Granite 4.2 30b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 30b leads 39.1 to 18.4.
- Granite 4.2 30b has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 | Granite 4.2 30b |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 29.1 | 41.8 |
| Rank | 316 | 130 |
| Context | 8K | — |
| Input $/M | $30 | — |
| Output $/M | $60 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4: 31.6 (#283)
- Granite 4.2 30b: 41.0 (#126)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Coding | 1254 | 1396 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- Granite 4.2 30b: —

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.8 (#289)
- Granite 4.2 30b: 27.8 (#112)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1374 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.8 (#309)
- Granite 4.2 30b: —

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#282)
- Granite 4.2 30b: 39.1 (#138)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Expert | 1211 | 1406 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multilingual

- GPT-4: 40.6 (#215)
- Granite 4.2 30b: 47.3 (#151)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | 1246 | 1340 |
| LMArena Chinese | 1242 | 1414 |
| LMArena Russian | 1251 | 1343 |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1261 | — |

## Instruction Following

- GPT-4: 65.3 (#222)
- Granite 4.2 30b: 71.2 (#155)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | 1241 | 1347 |

## Long Context

- GPT-4: 37.7 (#212)
- Granite 4.2 30b: 41.4 (#140)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | 1244 | 1359 |

## Writing & Preference

- GPT-4: 34.9 (#268)
- Granite 4.2 30b: 53.8 (#156)

| Benchmark | GPT-4 | Granite 4.2 30b |
|---|---|---|
| LMArena Text | 1263 | 1361 |
| LMArena Creative Writing | 1244 | 1288 |
| LMArena Multi-Turn | 1257 | 1339 |
| EQ-Bench Creative Writing | 752 | — |

## FAQ

### Is GPT-4 better than Granite 4.2 30b?

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 29.1 on the Noometry Index.

### Is GPT-4 or Granite 4.2 30b better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 31.6 in the Noometry coding category.

### How many benchmarks do GPT-4 and Granite 4.2 30b share?

11 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Granite 4.2 30b has 11.