MiniMax M3

minimax/minimax-m3-20260531

MiniMax M3 is an AI model from minimax that processes text, image, and video inputs and produces text output. It supports tool usage and reasoning, offers a context length of 1,048,576 tokens, provides open weights, and is priced at $0.3 per million input tokens and $1.2 per million output tokens. The model was released on 2026‑06‑01.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providerminimax
releasedMay 31, 2026
context1.0M
input / M$0.30

Specifications

What the API gives you

Context window
1.0M tokens
Max output
512K tokens
Input price
$0.30 / 1M tokens
Output price
$1.20 / 1M tokens
Cache read
$0.060 / 1M tokens
Modalities
text, image, video → text
Knowledge cutoff
—
Released
May 31, 2026

Measured evidence

Public benchmark record

Design Arena Coding
1248 Elo2026-10-20
Design Arena Full-stack Agent
1197 Elo2026-10-14
Design Arena UI
1248 Elo2026-10-20
Design Arena Web-app Agent
1198 Elo2026-10-20
Design Arena Website
1258 Elo2026-10-20
GPQA Diamond (Epoch AI)
90.9% ± 22026-08-10evaluated 2026-08-10
LiveBench Agentic Coding
40.7%2026-10-18
LiveBench Coding
68.2%2026-10-18
LiveBench Data Analysis
76.2%2026-10-18
LiveBench Instruction Following
57.5%2026-10-18
LiveBench Language
76.8%2026-10-18
LiveBench Math
77.0%2026-10-18
LiveBench Reasoning
74.5%2026-10-18
LMArena Agent
-9.52026-10-19
LMArena Agent Bash Recovery
0.62026-10-08
LMArena Agent Steerability
-9.72026-10-19
LMArena Agent Task Outcome
-15.52026-10-19
LMArena Agent Tool Hallucination
-1.92026-10-19
LMArena Creative Writing
1404 Elo2026-10-15
LMArena Instruction Following
1433 Elo2026-10-15
LMArena Long Query
1446 Elo2026-10-15
LMArena Math
1429 Elo2026-10-15
LMArena Text
1441 Elo2026-10-15
LMArena Text Factuality
1435 Elo2026-10-15
LMArena Vision
1233 Elo2026-10-19
LMArena Vision Diagrams
1261 Elo2026-10-19
LMArena Vision OCR
1246 Elo2026-10-19
LMArena WebDev
1482 Elo2026-10-19
LMArena WebDev Image-to-Web
1470 Elo2026-10-19
OTIS Mock AIME (Epoch AI)
71.1% ± 6.82026-08-10evaluated 2026-08-10
SWE-rebench (2026-05-15 to 2026-07-01)‡
47.2% ± 1.12026-10-20tools, tasks 2026-05-15 to 2026-07-01

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Business WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingEstablished evidence

    100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIEstablished evidence

    100% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

Show all 45 tasks
  • Best LLM for WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Roleplay & CharacterEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    92% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for a General AssistantEstablished evidence

    91% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Competition MathEstablished evidence

    81% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionEstablished evidence

    79% of intended weighted task evidence across 2 independent sources. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingEstablished evidence

    75% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    71% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Debugging & Code ReviewEstablished evidence

    67% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best Open-Weight LLM for Self-HostingEstablished evidence

    64% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsEstablished evidence

    63% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best Local LLM for CodingEstablished evidence

    62% of intended weighted task evidence across 3 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Image UnderstandingEstablished evidence

    61% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Document SummarizationEstablished evidence

    60% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationEstablished evidence

    60% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best Value LLMEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Literary TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Everyday TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsEstablished evidence

    48% of intended weighted task evidence across 3 independent sources. 9 of 9 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentEstablished evidence

    41% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsEstablished evidence

    41% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseEstablished evidence

    41% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawEstablished evidence

    41% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for JSON & Schema OutputEstablished evidence

    35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Structured Data ExtractionEstablished evidence

    35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Vision & DocumentsProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    58% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for RAG & Long ContextProvisional evidence

    39% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Tool & Function CallingProvisional evidence

    38% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Search. 6 of 7 configured evaluation feeds currently have results.

  • Best LLM for High-Volume ExtractionProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 1 of 3 configured evaluation feeds currently have results.

  • Best LLM for Computer & Browser UseProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    14% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from CRAG or SimpleQA Verified (Epoch AI). 5 of 7 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

  1. #8Best LLM for High-Volume Extraction

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.