AI - Paski.devMiniMax M3
MiniMax llmMiniMax's first natively multimodal open-weight flagship, introducing MiniMax Sparse Attention for a 1M-token context alongside frontier agentic coding.
overall ⌄
65.1
16 of 93 ranked
price · $/M tokens
0.3 / 1.2
in / out, as of 2026-07-25
to run it yourself ⌄
257 GB
minimum · 1.0 TB recommended
Benchmarks
What its maker published, and what anyone else measured. Every figure links the document it came from.
| benchmark | published | measured |
|---|---|---|
| SWE-bench | 80.5 | — |
| SWE-bench Pro | 59 | — |
| BrowseComp | 83.5 | — |
Cheaper, and at least as good
On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.
| DeepSeek V4-Pro DeepSeek | $0.00130 | overall 68.3 |
Lineage
No recorded lineage — root or standalone model.
Metadata
| org | MiniMax |
| released | 2026-06-01 |
| params | 428B-A23B |
| license | minimax-community |
| hf id | MiniMaxAI/MiniMax-M3 |