# Granite 3.0 8b Instruct vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 31.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-8b-instruct-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 1 category and Qwen2.5-Coder-32B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2.5-Coder-32B leads 38.0 to 27.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 35.4% for Granite 3.0 8b Instruct and 58% for Qwen2.5-Coder-32B.

## Snapshot

| | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 31.1 | 32.9 |
| Rank | 266 | 239 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Open | Open |

## Coding

- Granite 3.0 8b Instruct: 29.1 (#297)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 29.3% | 49% |
| LMArena Coding | 1113 | 1276 |
| BigCodeBench Complete | 35.4% | 58% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LiveBench Coding | — | 56.9% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- Granite 3.0 8b Instruct: 20.0 (#227)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1092 | 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 3.0 8b Instruct: 30.3 (#211)
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1143 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- Granite 3.0 8b Instruct: 29.1 (#233)
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1087 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- Granite 3.0 8b Instruct: 27.4 (#271)
- Qwen2.5-Coder-32B: 38.0 (#230)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1037 | 1205 |
| LMArena Chinese | 1063 | 1222 |
| LMArena Russian | 1060 | 1228 |

## Instruction Following

- Granite 3.0 8b Instruct: 56.2 (#271)
- Qwen2.5-Coder-32B: 61.6 (#240)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1088 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Granite 3.0 8b Instruct: 34.0 (#247)
- Qwen2.5-Coder-32B: 37.9 (#204)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1122 | 1251 |

## Writing & Preference

- Granite 3.0 8b Instruct: 31.2 (#280)
- Qwen2.5-Coder-32B: 41.8 (#235)

| Benchmark | Granite 3.0 8b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1096 | 1230 |
| LMArena Creative Writing | 1071 | 1174 |
| LMArena Multi-Turn | 1063 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Granite 3.0 8b Instruct better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 31.1 on the Noometry Index.

### Is Granite 3.0 8b Instruct or Qwen2.5-Coder-32B better for coding?

Granite 3.0 8b Instruct scores higher on coding benchmarks: 29.1 versus 22.4 in the Noometry coding category.

### How many benchmarks do Granite 3.0 8b Instruct and Qwen2.5-Coder-32B share?

14 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and Qwen2.5-Coder-32B has 31.