# Granite 4.0 Micro vs Mercury 2

> Mercury 2 is the stronger model overall, scoring 39.1 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 9.2× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/granite-4-0-micro-vs-mercury-2
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 9.9.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Granite 4.0 Micro accepts more context: 131K tokens versus 128K.
- Granite 4.0 Micro has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| Provider | IBM | Inception |
| Noometry Index | 29.0 | 39.1 |
| Rank | 318 | 175 |
| Context | 131K | 128K |
| Input $/M | $0.017 | $0.25 |
| Output $/M | $0.11 | $0.75 |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 Micro: —
- Mercury 2: 33.5 (#255)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| LMArena Coding | — | 1391 |
| ALE-Bench | — | 785.58 |

## Reasoning

- Granite 4.0 Micro: 19.2 (#265)
- Mercury 2: 23.8 (#170)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| CritPt | — | 0.8% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1362 |

## Math

- Granite 4.0 Micro: 12.0 (#307)
- Mercury 2: —

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| Omni-MATH | 20.9% | — |

## Knowledge

- Granite 4.0 Micro: 9.9 (#304)
- Mercury 2: 36.2 (#172)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| GPQA Diamond | 28.3% | — |
| MMLU-Pro | 39.5% | — |
| Vectara Hallucination Rate | — | 12.3% |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1358 |

## Multilingual

- Granite 4.0 Micro: —
- Mercury 2: 46.6 (#157)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1417 |
| LMArena Russian | — | 1304 |

## Instruction Following

- Granite 4.0 Micro: 69.9 (#169)
- Mercury 2: 70.2 (#165)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1329 |

## Long Context

- Granite 4.0 Micro: —
- Mercury 2: 40.5 (#154)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1330 |

## Writing & Preference

- Granite 4.0 Micro: 46.7 (#216)
- Mercury 2: 53.8 (#155)

| Benchmark | Granite 4.0 Micro | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1358 |

## FAQ

### Is Granite 4.0 Micro better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 9.2× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

### Which is cheaper, Granite 4.0 Micro or Mercury 2?

Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Which has the bigger context window?

Granite 4.0 Micro does, with 131K tokens against 128K.

### How many benchmarks do Granite 4.0 Micro and Mercury 2 share?

0 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Mercury 2 has 17.