MiniMax-Text-01 — benchmark results
MiniMax's open 456B MoE (45.9B active) with hybrid Lightning Attention and up to a 4M-token inference context (January 2025). Provider: MiniMax. Released 2025-01-14. Access: Open.
Unified ELO 1536 ± 18, rank #660 of 1776 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ProLLM - Entity Extraction | 85.1 | Score (%) | 91.5 |
| LongBench v2 | 56.5 | Accuracy (%) | 79.4 |
| ProLLM - Q&A Assistant | 95.3 | Score (%) | 64.7 |
| ProLLM - StackEval | 92.8 | Score (%) | 58.1 |
| SuperGPQA | 45.11 | Accuracy (%) | 52.9 |
| LLM Arena RU | 1021 | Arena Elo | 52.7 |
| LLM2014 Logic 2025-01 | 38.04 | Score (%) | 46.4 |
| ProLLM - SQL Disambiguation | 32.5 | Score (%) | 45.1 |
| ProLLM - Summarization | 72.3 | Score (%) | 42.2 |
| ProLLM - Function Calling | 85.5 | Score (%) | 37 |
| Elimination Game (Lechmazur) | 3.45 | TrueSkill μ | 28.8 |
| NYT Connections Older Models | 14.3 | Score (%) | 15.7 |
Interactive version: theaggregate.ai/model?slug=minimax-text-01 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.