# Granite 4.2 8B vs MiniMax-M2

> Granite 4.2 8B is the stronger model overall, scoring 40.0 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-8b-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 3 categories and MiniMax-M2 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.2 8B leads 25.5 to 18.6.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 131K.

## Snapshot

| | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 40.0 | 36.9 |
| Rank | 143 | 201 |
| Context | 131K | 205K |
| Input $/M | $0.06 | $0.30 |
| Output $/M | $0.25 | $1.20 |
| Weights | Open | Open |

## Coding

- Granite 4.2 8B: 39.9 (#138)
- MiniMax-M2: 39.1 (#151)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1379 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |

## Agentic & Tool Use

- Granite 4.2 8B: —
- MiniMax-M2: 24.9 (#102)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- Granite 4.2 8B: 25.5 (#130)
- MiniMax-M2: 18.6 (#256)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1327 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |

## Math

- Granite 4.2 8B: —
- MiniMax-M2: 34.6 (#158)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1350 |

## Knowledge

- Granite 4.2 8B: 37.7 (#144)
- MiniMax-M2: 36.3 (#160)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1380 | 1336 |

## Multilingual

- Granite 4.2 8B: 44.5 (#173)
- MiniMax-M2: 45.6 (#165)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1299 | 1314 |
| LMArena Chinese | 1361 | 1367 |
| LMArena Russian | 1283 | 1332 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- Granite 4.2 8B: 68.7 (#183)
- MiniMax-M2: 70.4 (#160)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1298 | 1329 |

## Long Context

- Granite 4.2 8B: 40.2 (#154)
- MiniMax-M2: 40.5 (#148)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1323 | 1332 |

## Writing & Preference

- Granite 4.2 8B: 49.8 (#183)
- MiniMax-M2: 53.3 (#157)

| Benchmark | Granite 4.2 8B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1319 | 1340 |
| LMArena Creative Writing | 1238 | 1288 |
| LMArena Multi-Turn | 1299 | 1362 |

## FAQ

### Is Granite 4.2 8B better than MiniMax-M2?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 36.9 on the Noometry Index.

### Which is cheaper, Granite 4.2 8B or MiniMax-M2?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

### Is Granite 4.2 8B or MiniMax-M2 better for coding?

They score almost the same on coding (39.9 vs 39.1); test both on your own repository before choosing.

### Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 131K.

### How many benchmarks do Granite 4.2 8B and MiniMax-M2 share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and MiniMax-M2 has 21.