# Granite 3.0 2b Instruct vs Granite 4.0 Micro

> Granite 3.0 2b Instruct is the stronger model overall, scoring 30.2 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-granite-4-0-micro
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Granite 3.0 2b Instruct leads 28.4 to 9.9.

## Snapshot

| | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 30.2 | 28.8 |
| Rank | 284 | 312 |
| Context | — | 131K |
| Input $/M | — | $0.017 |
| Output $/M | — | $0.11 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 27.8 (#311)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| BigCodeBench Instruct | 20.5% | — |
| LMArena Coding | 1090 | — |

## Reasoning

- Granite 3.0 2b Instruct: 19.6 (#234)
- Granite 4.0 Micro: 18.5 (#261)

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1073 | — |

## Math

- Granite 3.0 2b Instruct: 29.7 (#215)
- Granite 4.0 Micro: 11.2 (#301)

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.8% |
| Omni-MATH | — | 20.9% |
| LMArena Math | 1117 | — |

## Knowledge

- Granite 3.0 2b Instruct: 28.4 (#238)
- Granite 4.0 Micro: 9.9 (#299)

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| GPQA Diamond | — | 28.3% |
| MMLU-Pro | — | 39.5% |
| GPQA (HELM) | — | 30.7% |
| LMArena Expert | 1064 | — |

## Multilingual

- Granite 3.0 2b Instruct: 27.1 (#273)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Non-English | 1033 | — |
| LMArena Chinese | 1070 | — |
| LMArena Russian | 1045 | — |

## Instruction Following

- Granite 3.0 2b Instruct: 54.2 (#279)
- Granite 4.0 Micro: 70.0 (#164)

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| IFEval | — | 84.9% |
| LMArena Instruction Following | 1056 | — |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#263)
- Granite 4.0 Micro: —

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Longer Query | 1071 | — |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.8 (#287)
- Granite 4.0 Micro: 46.7 (#212)

| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 Micro |
|---|---|---|
| LMArena Text | 1080 | — |
| LMArena Creative Writing | 1046 | — |
| WildBench | — | 67% |
| LMArena Multi-Turn | 1053 | — |

## FAQ

### Is Granite 3.0 2b Instruct better than Granite 4.0 Micro?

Granite 3.0 2b Instruct is the stronger model overall, scoring 30.2 to 28.8 on the Noometry Index.

### How many benchmarks do Granite 3.0 2b Instruct and Granite 4.0 Micro share?

0 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Granite 4.0 Micro has 8.