# Granite 3.0 2b Instruct vs Mercury

> Mercury is the stronger model overall, scoring 37.6 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-mercury
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 1 category and Mercury in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 29.6.
- Granite 3.0 2b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| Provider | IBM | Inception |
| Noometry Index | 30.8 | 37.6 |
| Rank | 286 | 199 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Granite 3.0 2b Instruct: 28.3 (#316)
- Mercury: 38.7 (#170)

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Coding | 1090 | 1322 |
| BigCodeBench Instruct | 20.5% | — |

## Reasoning

- Granite 3.0 2b Instruct: 20.5 (#235)
- Mercury: 17.5 (#293)

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |

## Math

- Granite 3.0 2b Instruct: 32.2 (#217)
- Mercury: —

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Math | 1117 | — |

## Knowledge

- Granite 3.0 2b Instruct: 29.0 (#241)
- Mercury: —

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Expert | 1064 | — |

## Multilingual

- Granite 3.0 2b Instruct: 27.0 (#278)
- Mercury: 41.6 (#206)

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Non-English | 1033 | 1260 |
| LMArena Chinese | 1070 | — |
| LMArena Russian | 1045 | — |

## Instruction Following

- Granite 3.0 2b Instruct: 53.9 (#284)
- Mercury: 65.2 (#224)

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Instruction Following | 1056 | 1239 |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#268)
- Mercury: 38.4 (#198)

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Longer Query | 1070 | 1266 |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.6 (#292)
- Mercury: 46.2 (#221)

| Benchmark | Granite 3.0 2b Instruct | Mercury |
|---|---|---|
| LMArena Text | 1080 | 1282 |
| LMArena Creative Writing | 1046 | 1191 |
| LMArena Multi-Turn | 1053 | 1282 |

## FAQ

### Is Granite 3.0 2b Instruct better than Mercury?

Mercury is the stronger model overall, scoring 37.6 to 30.8 on the Noometry Index.

### Is Granite 3.0 2b Instruct or Mercury better for coding?

Mercury scores higher on coding benchmarks: 38.7 versus 28.3 in the Noometry coding category.

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

8 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Mercury has 9.