# Llama 3.2 90B vs MiniMax-M2

> MiniMax-M2 is the stronger model overall, scoring 36.9 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where MiniMax-M2 leads 34.6 to 10.4.

## Snapshot

| | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 27.1 | 36.9 |
| Rank | 326 | 201 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Llama 3.2 90B: —
- MiniMax-M2: 39.1 (#151)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| LMArena Coding | — | 1370 |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- MiniMax-M2: 24.9 (#102)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| BALROG | 27.3% | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- MiniMax-M2: 18.6 (#256)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1357 |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- MiniMax-M2: 34.6 (#158)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1350 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- MiniMax-M2: 36.3 (#160)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1336 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- MiniMax-M2: —

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- MiniMax-M2: 45.6 (#165)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1314 |
| LMArena Chinese | — | 1367 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Russian | — | 1332 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- Llama 3.2 90B: —
- MiniMax-M2: 70.4 (#160)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |

## Long Context

- Llama 3.2 90B: —
- MiniMax-M2: 40.5 (#148)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1332 |

## Writing & Preference

- Llama 3.2 90B: —
- MiniMax-M2: 53.3 (#157)

| Benchmark | Llama 3.2 90B | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1362 |

## FAQ

### Is Llama 3.2 90B better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 36.9 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and MiniMax-M2 share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and MiniMax-M2 has 21.