Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is MiniMax-M3?

108 SI-IQ · 90% interval 102–114
Rank 63 of 80 ranked models · Plausible rank range 44–68

MiniMax-M3 is a model from MiniMax, released on Jun 1, 2026. Its SI-IQ is 108 (90% interval 102–114), estimated from 5 benchmark results by 2 independent evaluators.

Facts

Developer
MiniMax
Released
Jun 1, 2026
Access
Open weights (restricted licence)
Benchmarks used
5 results from 2 evaluators

Ability by area (SI-IQ, 90% interval)

6080100120140160Reasoning104

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark Area Score Implied SI-IQ Evaluated by As listed by the source Retrieved Source
Chess Puzzles Reasoning 13.0% 102 Epoch AI MiniMax-M3 Oct 18, 2026 Epoch AI Benchmarking Hub · data file
Mystery Game Puzzles Reasoning 8.0% 70 Epoch AI MiniMax-M3_none Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 71.1% 103 Epoch AI MiniMax-M3 Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 90.9% 126 Epoch AI MiniMax-M3 Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 91.5% 134 OpenRouter minimax/minimax-m3-20260531
Minimax · first-party provider (1 of 14 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file
τ²-bench Airline (OpenRouter run) Agents 73.9% 127 OpenRouter minimax/minimax-m3-20260531
Minimax · first-party provider (1 of 14 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, MiniMax-M3 has a rating of 1,441 (1,437–1,445) from 63,973 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

ModelSI-IQ
Gemini 2.5 Pro (Jun 2025)Google DeepMind108MiniMax-M3 vs Gemini 2.5 Pro (Jun 2025)
Gemini 3.5 Flash-LiteGoogle DeepMind109MiniMax-M3 vs Gemini 3.5 Flash-Lite
Claude Sonnet 4.5Anthropic110MiniMax-M3 vs Claude Sonnet 4.5
gpt-oss-120bOpenAI106MiniMax-M3 vs gpt-oss-120b
Qwen 3.6 35B-A3BAlibaba111MiniMax-M3 vs Qwen 3.6 35B-A3B

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..