# Granite 4.2 3b vs Qwen1.5-72B

> Granite 4.2 3b is the stronger model overall, scoring 39.4 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 7 categories and Qwen1.5-72B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 3b leads 36.3 to 11.5.

## Snapshot

| | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 39.4 | 30.8 |
| Rank | 169 | 285 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 40.0 (#151)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1361 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Reasoning

- Granite 4.2 3b: 26.0 (#138)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1306 | 1148 |

## Math

- Granite 4.2 3b: —
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |

## Knowledge

- Granite 4.2 3b: 36.3 (#171)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1315 | 1136 |
| GPQA Diamond | — | 28.8% |

## Multilingual

- Granite 4.2 3b: 42.1 (#198)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1268 | 1135 |
| LMArena Chinese | 1269 | 1186 |
| LMArena Russian | 1249 | 1104 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Granite 4.2 3b: 67.1 (#200)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1273 | 1141 |

## Long Context

- Granite 4.2 3b: 39.2 (#185)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1291 | 1157 |

## Writing & Preference

- Granite 4.2 3b: 47.2 (#212)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Granite 4.2 3b | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1293 | 1166 |
| LMArena Creative Writing | 1205 | 1137 |
| LMArena Multi-Turn | 1290 | 1160 |

## FAQ

### Is Granite 4.2 3b better than Qwen1.5-72B?

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 30.8 on the Noometry Index.

### Is Granite 4.2 3b or Qwen1.5-72B better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 31.9 in the Noometry coding category.

### How many benchmarks do Granite 4.2 3b and Qwen1.5-72B share?

11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Qwen1.5-72B has 22.