# Granite 3.1 8b Instruct vs MiniMax-M2

> MiniMax-M2 is the stronger model overall, scoring 36.9 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 1 category and MiniMax-M2 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2 leads 53.3 to 35.7.

## Snapshot

| | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 31.8 | 36.9 |
| Rank | 256 | 201 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 33.9 (#232)
- MiniMax-M2: 39.1 (#151)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1186 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 23.9 (#113)
- MiniMax-M2: 24.9 (#102)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Berkeley Function Calling Leaderboard | 27.1% | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- Granite 3.1 8b Instruct: 21.2 (#204)
- MiniMax-M2: 18.6 (#256)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |

## Math

- Granite 3.1 8b Instruct: 30.4 (#210)
- MiniMax-M2: 34.6 (#158)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1152 | 1350 |

## Knowledge

- Granite 3.1 8b Instruct: 30.6 (#218)
- MiniMax-M2: 36.3 (#160)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1142 | 1336 |

## Multilingual

- Granite 3.1 8b Instruct: 31.1 (#255)
- MiniMax-M2: 45.6 (#165)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1099 | 1314 |
| LMArena Chinese | 1145 | 1367 |
| LMArena Russian | 1092 | 1332 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.9 (#254)
- MiniMax-M2: 70.4 (#160)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1131 | 1329 |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#236)
- MiniMax-M2: 40.5 (#148)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1162 | 1332 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.7 (#261)
- MiniMax-M2: 53.3 (#157)

| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1150 | 1340 |
| LMArena Creative Writing | 1129 | 1288 |
| LMArena Multi-Turn | 1108 | 1362 |

## FAQ

### Is Granite 3.1 8b Instruct better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 36.9 to 31.8 on the Noometry Index.

### Is Granite 3.1 8b Instruct or MiniMax-M2 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 33.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and MiniMax-M2 share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and MiniMax-M2 has 21.