MiniMax-M3.1-Flash: benchmark results
Provider: MiniMax. Released 2026-10-19. Access: API.
Aggregate Rating 1848 ± 24, rank #33 of 1656 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (AutomationBench v1.0.6) | 62.2 | Score (%) | 100 |
| AutomationBench-AA | 72.52 | Guardrail-Adjusted Objective Completion (%) | 99.6 |
| AutomationBench-AA - Finance - Raw Objective Completion | 93.72 | Raw Objective Completion (%) | 99.6 |
| AutomationBench-AA - HR - Raw Objective Completion | 77.5 | Raw Objective Completion (%) | 97.8 |
| AutomationBench-AA - Strict | 38.05 | Strict Task Success (%) | 96.9 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 80 | Omniscience Index | 96.1 |
| AA-Omniscience Index - Software Engineering (SWE) - R | 56 | Omniscience Index | 96.1 |
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 80 | Omniscience Index | 95.9 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 78 | Omniscience Index | 95.7 |
| AA Humanity's Last Exam | 47.96 | Accuracy (%) | 95.1 |
| AutomationBench-AA - Marketing - Raw Objective Completion | 88.22 | Raw Objective Completion (%) | 94.7 |
| AutomationBench-AA - Support - Raw Objective Completion | 90.08 | Raw Objective Completion (%) | 94.7 |
Interactive version: theaggregate.ai/model?slug=minimax-m3-1-flash · How It Works · Data refreshed daily, snapshot 2026-10-20.