# Granite 4.0 Micro vs Mercury

> Mercury is the stronger model overall, scoring 37.6 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-0-micro-vs-mercury
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in instruction following, where Granite 4.0 Micro leads 69.9 to 65.2.
- Granite 4.0 Micro has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 Micro | Mercury |
|---|---|---|
| Provider | IBM | Inception |
| Noometry Index | 29.0 | 37.6 |
| Rank | 318 | 199 |
| Context | 131K | — |
| Input $/M | $0.017 | — |
| Output $/M | $0.11 | — |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 Micro: —
- Mercury: 38.7 (#170)

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| LMArena Coding | — | 1322 |

## Reasoning

- Granite 4.0 Micro: 19.2 (#265)
- Mercury: 17.5 (#293)

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| Kagi LLM Benchmark | — | 21.6% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1285 |

## Math

- Granite 4.0 Micro: 12.0 (#307)
- Mercury: —

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| Omni-MATH | 20.9% | — |

## Knowledge

- Granite 4.0 Micro: 9.9 (#304)
- Mercury: —

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| GPQA Diamond | 28.3% | — |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |

## Multilingual

- Granite 4.0 Micro: —
- Mercury: 41.6 (#206)

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| LMArena Non-English | — | 1260 |

## Instruction Following

- Granite 4.0 Micro: 69.9 (#169)
- Mercury: 65.2 (#224)

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1239 |

## Long Context

- Granite 4.0 Micro: —
- Mercury: 38.4 (#198)

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1266 |

## Writing & Preference

- Granite 4.0 Micro: 46.7 (#216)
- Mercury: 46.2 (#221)

| Benchmark | Granite 4.0 Micro | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1191 |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1282 |

## FAQ

### Is Granite 4.0 Micro better than Mercury?

Mercury is the stronger model overall, scoring 37.6 to 29.0 on the Noometry Index.

### How many benchmarks do Granite 4.0 Micro and Mercury share?

0 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Mercury has 9.