# Granite 4.2 3b vs Qwen1.5-7B

> Granite 4.2 3b is the stronger model overall, scoring 39.4 to 31.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-qwen1-5-7b
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 7 categories and Qwen1.5-7B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.2 3b leads 47.2 to 29.6.

## Snapshot

| | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 39.4 | 31.4 |
| Rank | 169 | 273 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 40.0 (#151)
- Qwen1.5-7B: 32.2 (#276)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1361 | 1107 |

## Reasoning

- Granite 4.2 3b: 26.0 (#138)
- Qwen1.5-7B: 20.4 (#240)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1306 | 1065 |

## Math

- Granite 4.2 3b: —
- Qwen1.5-7B: 31.4 (#224)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Math | — | 1080 |

## Knowledge

- Granite 4.2 3b: 36.3 (#171)
- Qwen1.5-7B: 28.7 (#243)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1315 | 1055 |
| MMLU | — | 62.6% |

## Multilingual

- Granite 4.2 3b: 42.1 (#198)
- Qwen1.5-7B: 28.5 (#271)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1268 | 1058 |
| LMArena Chinese | 1269 | 1141 |
| LMArena Russian | 1249 | 1006 |

## Instruction Following

- Granite 4.2 3b: 67.1 (#200)
- Qwen1.5-7B: 54.1 (#281)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1273 | 1058 |

## Long Context

- Granite 4.2 3b: 39.2 (#185)
- Qwen1.5-7B: 33.1 (#266)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1291 | 1090 |

## Writing & Preference

- Granite 4.2 3b: 47.2 (#212)
- Qwen1.5-7B: 29.6 (#293)

| Benchmark | Granite 4.2 3b | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1293 | 1083 |
| LMArena Creative Writing | 1205 | 1035 |
| LMArena Multi-Turn | 1290 | 1062 |

## FAQ

### Is Granite 4.2 3b better than Qwen1.5-7B?

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 31.4 on the Noometry Index.

### Is Granite 4.2 3b or Qwen1.5-7B better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 32.2 in the Noometry coding category.

### How many benchmarks do Granite 4.2 3b and Qwen1.5-7B share?

11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Qwen1.5-7B has 13.