# Llama 3.1-405B vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-405b-vs-minimax-m3
- Last updated: 2026-10-12
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and MiniMax-M3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 30.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 71.1% for MiniMax-M3.

## Snapshot

| | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 30.7 | 43.8 |
| Rank | 288 | 85 |
| Context | — | 1M |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Llama 3.1-405B: 33.1 (#262)
- MiniMax-M3: 41.8 (#118)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1291 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| WeirdML | 21.4% | — |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- Llama 3.1-405B: 21.0 (#140)
- MiniMax-M3: 22.6 (#130)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Llama 3.1-405B: 16.8 (#300)
- MiniMax-M3: 30.1 (#87)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| SimpleBench | 23% | 45.8% |
| LMArena Hard Prompts | 1269 | 1447 |
| DTBench | 61.4% | 78.9% |
| Epoch Capabilities Index | 128.75 | 146.95 |
| ForecastBench | 59.9 | 61.4 |
| Kagi LLM Benchmark | 45% | — |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| BIG-Bench Hard | 82.9% | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |

## Math

- Llama 3.1-405B: 18.4 (#290)
- MiniMax-M3: 40.0 (#95)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 71.1% |
| LMArena Math | 1281 | 1429 |
| ProofBench | — | 18% |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |

## Knowledge

- Llama 3.1-405B: 30.4 (#227)
- MiniMax-M3: 58.4 (#35)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 50.9% | 90.9% |
| LMArena Expert | 1243 | 1461 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |

## Multimodal

- Llama 3.1-405B: —
- MiniMax-M3: 40.2 (#51)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- Llama 3.1-405B: 40.7 (#214)
- MiniMax-M3: 53.0 (#75)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1248 | 1420 |
| LMArena Chinese | 1242 | 1463 |
| LMArena French | 1279 | 1447 |
| LMArena German | 1252 | 1426 |
| LMArena Japanese | 1208 | 1381 |
| LMArena Korean | 1184 | 1372 |
| LMArena Russian | 1265 | 1428 |
| LMArena Spanish | 1260 | 1432 |

## Instruction Following

- Llama 3.1-405B: 65.9 (#214)
- MiniMax-M3: 75.5 (#62)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1259 | 1433 |
| IFEval | 81.1% | — |

## Long Context

- Llama 3.1-405B: 38.4 (#197)
- MiniMax-M3: 44.2 (#72)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1266 | 1445 |

## Writing & Preference

- Llama 3.1-405B: 38.9 (#251)
- MiniMax-M3: 62.1 (#83)

| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1284 | 1433 |
| LMArena Creative Writing | 1262 | 1404 |
| LMArena Multi-Turn | 1297 | 1442 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Llama 3.1-405B better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.7 on the Noometry Index.

### Is Llama 3.1-405B or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 33.1 in the Noometry coding category.

### How many benchmarks do Llama 3.1-405B and MiniMax-M3 share?

23 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and MiniMax-M3 has 41.