# Granite 3.1 8b Instruct vs Qwen1.5-7B

> Granite 3.1 8b Instruct and Qwen1.5-7B score almost the same on the Noometry Index (32.4 vs 31.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-qwen1-5-7b
- 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 8 categories and Qwen1.5-7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 3.1 8b Instruct leads 35.5 to 29.6.

## Snapshot

| | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 32.4 | 31.4 |
| Rank | 258 | 273 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 34.5 (#233)
- Qwen1.5-7B: 32.2 (#276)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1186 | 1107 |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 24.1 (#120)
- Qwen1.5-7B: —

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 22.1 (#207)
- Qwen1.5-7B: 20.4 (#240)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1065 |

## Math

- Granite 3.1 8b Instruct: 33.0 (#209)
- Qwen1.5-7B: 31.4 (#224)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1152 | 1080 |

## Knowledge

- Granite 3.1 8b Instruct: 31.1 (#220)
- Qwen1.5-7B: 28.7 (#243)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1142 | 1055 |
| MMLU | — | 62.6% |

## Multilingual

- Granite 3.1 8b Instruct: 30.9 (#260)
- Qwen1.5-7B: 28.5 (#271)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1099 | 1058 |
| LMArena Chinese | 1145 | 1141 |
| LMArena Russian | 1092 | 1006 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.6 (#259)
- Qwen1.5-7B: 54.1 (#281)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1058 |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#241)
- Qwen1.5-7B: 33.1 (#266)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1162 | 1090 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.5 (#266)
- Qwen1.5-7B: 29.6 (#293)

| Benchmark | Granite 3.1 8b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1150 | 1083 |
| LMArena Creative Writing | 1129 | 1035 |
| LMArena Multi-Turn | 1108 | 1062 |

## FAQ

### Is Granite 3.1 8b Instruct better than Qwen1.5-7B?

Granite 3.1 8b Instruct and Qwen1.5-7B score almost the same on the Noometry Index (32.4 vs 31.4), so choose on price, context window or the category you care about most.

### Is Granite 3.1 8b Instruct or Qwen1.5-7B better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 32.2 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Qwen1.5-7B share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Qwen1.5-7B has 13.