Model comparison
Llama 3.2 90B vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
MiniMaxSummary
- The widest gap is in math, where MiniMax-M2.1 leads 35.6 to 10.4.
Side by side
| Llama 3.2 90B | MiniMax-M2.1 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 27.1 | 38.4 |
| Released | 2024-09-24 | 2025-12-23 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 9 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, MiniMax-M2.1: 40.1 (#132)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | — | 1384 |
| LMArena Coding | — | 1421 |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Llama 3.2 90B leads
Llama 3.2 90B: 29.7 (#73), MiniMax-M2.1: 27.7 (#91)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| BALROG | 27.3% | — |
Reasoning Llama 3.2 90B leads
Llama 3.2 90B: 20.9 (#207), MiniMax-M2.1: 15.8 (#301)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| NYT Connections (extended) | — | 11.2% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1410 |
| Epoch Capabilities Index | 125.5 | — |
Math MiniMax-M2.1 leads
Llama 3.2 90B: 10.4 (#302), MiniMax-M2.1: 35.6 (#142)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1396 |
| MATH Level 5 | 39.4% | — |
Knowledge MiniMax-M2.1 leads
Llama 3.2 90B: 21.7 (#269), MiniMax-M2.1: 37.7 (#143)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| GPQA Diamond | 41% | — |
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1432 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 24.9 (#119), MiniMax-M2.1: —
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, MiniMax-M2.1: 50.2 (#123)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | — | 1378 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1405 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1297 |
| LMArena Russian | — | 1386 |
| LMArena Spanish | — | 1396 |
Instruction Following Not comparable
Llama 3.2 90B: —, MiniMax-M2.1: 74.0 (#108)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | — | 1399 |
Long Context Not comparable
Llama 3.2 90B: —, MiniMax-M2.1: 43.2 (#98)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | — | 1416 |
Writing & Preference Not comparable
Llama 3.2 90B: —, MiniMax-M2.1: 58.5 (#114)
| Benchmark | Llama 3.2 90B | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | — | 1392 |
| LMArena Creative Writing | — | 1362 |
| LMArena Multi-Turn | — | 1396 |
Frequently asked questions
Is Llama 3.2 90B better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 27.1 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and MiniMax-M2.1 share?
0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and MiniMax-M2.1 has 22.