# Granite 3.1 8b Instruct vs Qwen2-72B

> Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 4 categories and Qwen2-72B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.1 8b Instruct leads 30.6 to 21.2.

## Snapshot

| | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 31.8 | 29.5 |
| Rank | 256 | 294 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 33.9 (#232)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1186 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 23.9 (#113)
- Qwen2-72B: 16.9 (#138)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Granite 3.1 8b Instruct: 21.2 (#204)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1191 |
| Epoch Capabilities Index | — | 125.27 |

## Math

- Granite 3.1 8b Instruct: 30.4 (#210)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1152 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Granite 3.1 8b Instruct: 30.6 (#218)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1142 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- Granite 3.1 8b Instruct: 31.1 (#255)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1099 | 1176 |
| LMArena Chinese | 1145 | 1240 |
| LMArena Russian | 1092 | 1169 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1168 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.9 (#254)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1181 |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#236)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1162 | 1193 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.7 (#261)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Granite 3.1 8b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1150 | 1203 |
| LMArena Creative Writing | 1129 | 1181 |
| LMArena Multi-Turn | 1108 | 1195 |

## FAQ

### Is Granite 3.1 8b Instruct better than Qwen2-72B?

Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 29.5 on the Noometry Index.

### Is Granite 3.1 8b Instruct or Qwen2-72B better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 28.7 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Qwen2-72B share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Qwen2-72B has 26.