# Llama 3.1-405B vs MiniMax-M2

> MiniMax-M2 is the stronger model overall, scoring 37.4 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-405b-vs-minimax-m2
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and MiniMax-M2 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 18.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 45% for Llama 3.1-405B and 57.8% for MiniMax-M2.

## Snapshot

| | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 30.7 | 37.4 |
| Rank | 288 | 204 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Llama 3.1-405B: 33.1 (#262)
- MiniMax-M2: 39.3 (#159)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1291 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| WeirdML | 21.4% | — |

## Agentic & Tool Use

- Llama 3.1-405B: 21.0 (#140)
- MiniMax-M2: 25.1 (#109)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- Llama 3.1-405B: 16.8 (#300)
- MiniMax-M2: 19.4 (#258)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 45% | 57.8% |
| LMArena Hard Prompts | 1269 | 1357 |
| SimpleBench | 23% | — |
| NYT Connections (extended) | — | 14.8% |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |

## Math

- Llama 3.1-405B: 18.4 (#290)
- MiniMax-M2: 37.3 (#160)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1281 | 1352 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |

## Knowledge

- Llama 3.1-405B: 30.4 (#227)
- MiniMax-M2: 37.0 (#163)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1243 | 1337 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |

## Multilingual

- Llama 3.1-405B: 40.7 (#214)
- MiniMax-M2: 45.3 (#171)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1248 | 1313 |
| LMArena Chinese | 1242 | 1366 |
| LMArena French | 1279 | 1335 |
| LMArena German | 1252 | 1355 |
| LMArena Russian | 1265 | 1331 |
| LMArena Spanish | 1260 | 1326 |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |

## Instruction Following

- Llama 3.1-405B: 65.9 (#214)
- MiniMax-M2: 70.2 (#166)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1259 | 1328 |
| IFEval | 81.1% | — |

## Long Context

- Llama 3.1-405B: 38.4 (#197)
- MiniMax-M2: 40.5 (#153)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1266 | 1331 |

## Writing & Preference

- Llama 3.1-405B: 38.9 (#251)
- MiniMax-M2: 53.0 (#162)

| Benchmark | Llama 3.1-405B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1284 | 1340 |
| LMArena Creative Writing | 1262 | 1286 |
| LMArena Multi-Turn | 1297 | 1361 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |

## FAQ

### Is Llama 3.1-405B better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 30.7 on the Noometry Index.

### Is Llama 3.1-405B or MiniMax-M2 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 33.1 in the Noometry coding category.

### How many benchmarks do Llama 3.1-405B and MiniMax-M2 share?

16 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and MiniMax-M2 has 21.