# Granite 4.1 8b vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.5 to 36.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-1-8b-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Granite 4.1 8b scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 35.5.

## Snapshot

| | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 36.8 | 43.5 |
| Rank | 202 | 81 |
| Context | — | 1M |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Granite 4.1 8b: 29.9 (#291)
- MiniMax-M3: 41.5 (#111)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1190 | 1482 |
| LMArena Coding | 1313 | 1470 |
| FrontierCode | — | 14.7% |
| SciCode | — | 47.1% |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- Granite 4.1 8b: —
- MiniMax-M3: 22.5 (#121)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Granite 4.1 8b: 24.6 (#142)
- MiniMax-M3: 29.3 (#83)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 1294 | 1447 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 147 |
| ForecastBench | — | 61.4 |

## Math

- Granite 4.1 8b: 33.8 (#167)
- MiniMax-M3: 39.1 (#83)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1311 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |

## Knowledge

- Granite 4.1 8b: 35.5 (#171)
- MiniMax-M3: 58.4 (#32)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1310 | 1462 |
| GPQA Diamond | — | 90.9% |

## Multimodal

- Granite 4.1 8b: —
- MiniMax-M3: 39.5 (#45)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |

## Multilingual

- Granite 4.1 8b: 41.8 (#199)
- MiniMax-M3: 53.2 (#70)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1261 | 1420 |
| LMArena Chinese | 1335 | 1465 |
| LMArena Russian | 1238 | 1430 |
| LMArena French | — | 1445 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Spanish | — | 1431 |

## Instruction Following

- Granite 4.1 8b: 67.0 (#198)
- MiniMax-M3: 75.7 (#56)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1268 | 1433 |

## Long Context

- Granite 4.1 8b: 38.7 (#188)
- MiniMax-M3: 44.2 (#68)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1275 | 1445 |

## Writing & Preference

- Granite 4.1 8b: 48.3 (#199)
- MiniMax-M3: 62.3 (#79)

| Benchmark | Granite 4.1 8b | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1291 | 1433 |
| LMArena Creative Writing | 1249 | 1405 |
| LMArena Multi-Turn | 1269 | 1441 |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Granite 4.1 8b better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 36.8 on the Noometry Index.

### Is Granite 4.1 8b or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 29.9 in the Noometry coding category.

### How many benchmarks do Granite 4.1 8b and MiniMax-M3 share?

13 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and MiniMax-M3 has 41.