MiniMax-M3 (Reasoning): benchmark results

Provider: MiniMax. Released 2026-06-01. Access: Open.

Aggregate Rating 1600 ± 16, rank #766 of 2287 rated models, from 140 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SEA-HELM (Burmese) - Sentiment Analysis48.67Normalized Score95.9
SEA-HELM (Indonesian) - Safety64.1Normalized Score94.6
SEA-HELM (Indonesian) - Toxicity Detection56Normalized Score94.6
SEA-HELM (Tamil) - SEA-Safeguard84.64Normalized Score94.6
SEA-HELM (Tamil) - Natural Language Inference55.35Normalized Score93.2
SEA-HELM (Burmese) - NLU64.61Normalized Score91.9
SEA-HELM (Tamil) - NLR74.78Normalized Score89.2
SEA-HELM (Vietnamese) - SEA-Safeguard80.31Normalized Score89.2
SEA-HELM (Indonesian) - Pragmatics74.72Normalized Score87.8
SEA-HELM (Indonesian) - Sentiment Analysis80.73Normalized Score87.8
SEA-HELM (Tamil) - SEA-MT-Bench (LLM Judge)82.19Normalized Score87.8
SEA-HELM (Tamil)72.89Normalized Score86.5

Interactive version: theaggregate.ai/model?slug=minimax-m3-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-22.