# Granite 3.1 8b Instruct vs Granite 4.0 Micro

> Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-granite-4-0-micro
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Granite 3.1 8b Instruct leads 31.1 to 9.9.

## Snapshot

| | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 32.4 | 29.0 |
| Rank | 258 | 318 |
| Context | — | 131K |
| Input $/M | — | $0.017 |
| Output $/M | — | $0.11 |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 34.5 (#233)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Coding | 1186 | — |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 24.1 (#120)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 22.1 (#207)
- Granite 4.0 Micro: 19.2 (#265)

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1145 | — |

## Math

- Granite 3.1 8b Instruct: 33.0 (#209)
- Granite 4.0 Micro: 12.0 (#307)

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.8% |
| Omni-MATH | — | 20.9% |
| LMArena Math | 1152 | — |

## Knowledge

- Granite 3.1 8b Instruct: 31.1 (#220)
- Granite 4.0 Micro: 9.9 (#304)

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| GPQA Diamond | — | 28.3% |
| MMLU-Pro | — | 39.5% |
| GPQA (HELM) | — | 30.7% |
| LMArena Expert | 1142 | — |

## Multilingual

- Granite 3.1 8b Instruct: 30.9 (#260)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Non-English | 1099 | — |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |

## Instruction Following

- Granite 3.1 8b Instruct: 58.6 (#259)
- Granite 4.0 Micro: 69.9 (#169)

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| IFEval | — | 84.9% |
| LMArena Instruction Following | 1131 | — |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#241)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Longer Query | 1162 | — |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.5 (#266)
- Granite 4.0 Micro: 46.7 (#216)

| Benchmark | Granite 3.1 8b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Text | 1150 | — |
| LMArena Creative Writing | 1129 | — |
| WildBench | — | 67% |
| LMArena Multi-Turn | 1108 | — |

## FAQ

### Is Granite 3.1 8b Instruct better than Granite 4.0 Micro?

Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 29.0 on the Noometry Index.

### How many benchmarks do Granite 3.1 8b Instruct and Granite 4.0 Micro share?

0 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Granite 4.0 Micro has 8.