# Granite 4.2 8B vs Qwen2.5-Coder-32B

> Granite 4.2 8B is the stronger model overall, scoring 40.0 to 32.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-8b-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 7 categories and Qwen2.5-Coder-32B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Granite 4.2 8B leads 39.9 to 22.4.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Granite 4.2 8B accepts more context: 131K tokens versus 33K.

## Snapshot

| | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 40.0 | 32.9 |
| Rank | 143 | 239 |
| Context | 131K | 33K |
| Input $/M | $0.06 | $0.66 |
| Output $/M | $0.25 | $1 |
| Weights | Open | Open |

## Coding

- Granite 4.2 8B: 39.9 (#138)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1379 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- Granite 4.2 8B: 25.5 (#130)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1327 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.41 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- Granite 4.2 8B: —
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | — | 46.6% |
| LMArena Math | — | 1251 |
| GSM8K | — | 93% |

## Knowledge

- Granite 4.2 8B: 37.7 (#144)
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1380 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- Granite 4.2 8B: 44.5 (#173)
- Qwen2.5-Coder-32B: 38.0 (#230)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1299 | 1205 |
| LMArena Chinese | 1361 | 1222 |
| LMArena Russian | 1283 | 1228 |

## Instruction Following

- Granite 4.2 8B: 68.7 (#183)
- Qwen2.5-Coder-32B: 61.6 (#240)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1298 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Granite 4.2 8B: 40.2 (#154)
- Qwen2.5-Coder-32B: 37.9 (#204)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1323 | 1251 |

## Writing & Preference

- Granite 4.2 8B: 49.8 (#183)
- Qwen2.5-Coder-32B: 41.8 (#235)

| Benchmark | Granite 4.2 8B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1319 | 1230 |
| LMArena Creative Writing | 1238 | 1174 |
| LMArena Multi-Turn | 1299 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Granite 4.2 8B better than Qwen2.5-Coder-32B?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 32.9 on the Noometry Index.

### Which is cheaper, Granite 4.2 8B or Qwen2.5-Coder-32B?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

### Is Granite 4.2 8B or Qwen2.5-Coder-32B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 22.4 in the Noometry coding category.

### Which has the bigger context window?

Granite 4.2 8B does, with 131K tokens against 33K.

### How many benchmarks do Granite 4.2 8B and Qwen2.5-Coder-32B share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Qwen2.5-Coder-32B has 31.