#27
MiniMax M3
MiniMax · Open Weight · Non-Reasoning · 1M context
59/ 100 composite
Released 2026-06-01
Benchmark Scores by Category
Coding
54.6
Knowledge
66.0
Agentic
63.3
Multimodal
48.1
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$0.3
per 1M tokens
Output
$1.2
per 1M tokens
Value Score
57.3
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: