Model comparison
Llama 3.1-405B vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.5 to 30.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Meta
MiniMaxSummary
- 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.
Side by side
| Llama 3.1-405B | MiniMax-M3 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 30.4 | 43.5 |
| Released | 2024-07-23 | 2026-06-01 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 512K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 42 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Llama 3.1-405B: 32.7 (#257), MiniMax-M3: 41.5 (#111)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1291 | 1470 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| WeirdML | 21.4% | — |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use MiniMax-M3 leads
Llama 3.1-405B: 20.9 (#131), MiniMax-M3: 22.5 (#121)
| 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 MiniMax-M3 leads
Llama 3.1-405B: 16.4 (#293), MiniMax-M3: 29.3 (#83)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| SimpleBench | 23% | 45.8% |
| LMArena Hard Prompts | 1270 | 1447 |
| DTBench | 61.4% | 78.9% |
| Epoch Capabilities Index | 128.76 | 147 |
| 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 MiniMax-M3 leads
Llama 3.1-405B: 17.3 (#283), MiniMax-M3: 39.1 (#83)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 71.1% |
| LMArena Math | 1281 | 1432 |
| ProofBench | — | 18% |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge MiniMax-M3 leads
Llama 3.1-405B: 30.4 (#221), MiniMax-M3: 58.4 (#32)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 50.9% | 90.9% |
| LMArena Expert | 1243 | 1462 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, MiniMax-M3: 39.5 (#45)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1254 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Llama 3.1-405B: 40.9 (#209), MiniMax-M3: 53.2 (#70)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1248 | 1420 |
| LMArena Chinese | 1242 | 1465 |
| LMArena French | 1278 | 1445 |
| LMArena German | 1252 | 1424 |
| LMArena Japanese | 1208 | 1381 |
| LMArena Korean | 1184 | 1372 |
| LMArena Russian | 1265 | 1430 |
| LMArena Spanish | 1259 | 1431 |
Instruction Following MiniMax-M3 leads
Llama 3.1-405B: 66.1 (#209), MiniMax-M3: 75.7 (#56)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1259 | 1433 |
| IFEval | 81.1% | — |
Long Context MiniMax-M3 leads
Llama 3.1-405B: 38.4 (#192), MiniMax-M3: 44.2 (#68)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1266 | 1445 |
Writing & Preference MiniMax-M3 leads
Llama 3.1-405B: 39.1 (#246), MiniMax-M3: 62.3 (#79)
| Benchmark | Llama 3.1-405B | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1284 | 1433 |
| LMArena Creative Writing | 1262 | 1405 |
| LMArena Multi-Turn | 1297 | 1441 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Llama 3.1-405B better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 30.4 on the Noometry Index.
Is Llama 3.1-405B or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 32.7 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.