Skip to content
Yardstick
  1. Models
  2. MiniMax
  3. MiniMax M3

MiniMax M3

MiniMax · Flagship · Jun 1, 2026Open weights

MiniMax's open-weight flagship: coding, a one-million-token context and image and video input at the low end of the price range.

Announcement (opens in a new tab)
Artificial Analysis Intelligence Index
29.2#23 of 29
API price per 1M tokens
$0.30 / $1.20input / output · $0.52 blended
Context window
1Mtokens
Output speed
94 t/s24s to first answer

Benchmark results

Each row shows this model (blue) against every other model in the catalogue (grey), worst on the left, best on the right.

Overall capability

  • Artificial Analysis Intelligence Index29.2#23 of 29
    11.357.6
  • Epoch Capabilities Index146.9#16 of 16
    146.9167.3
  • LiveBench67.3%#22 of 23
    63.9%83.4%

Coding

  • Arena WebDev1,482#21 of 27
    1,2631,814

Agents & professional work

  • GDPval-AA1,242#18 of 18
    1,2421,866
  • Vending-Bench 2$2,158#9 of 9
    $2,158$15,515

Reasoning

  • SimpleBench45.8%#12 of 12
    45.8%88.4%

Knowledge & science

  • GPQA Diamond90.9%#10 of 14
    90.2%95.8%

Multimodal

  • Arena Vision1,237#14 of 15
    1,1991,301

Human preference

  • Arena Text1,440#21 of 24
    1,4251,525

Specs & pricing

Developer
MiniMax
Released
Jun 1, 2026
Availability
Generally available
API model ID
MiniMax-M3
Weights
Open · MiniMax Community License
Parameters
428B (MoE)
Reasoning
Adjustable effort
Accepts
Text, Image, Video
Produces
Text
Context window
1,000,000 tokens
Input price
$0.30 / 1M tokens
Output price
$1.20 / 1M tokens
Cached input
$0.06 / 1M tokens

Effective price after MiniMax's permanent 50% discount, for requests up to 512K input tokens.

Closest alternatives

Models from other labs nearest to MiniMax M3 on Artificial Analysis Intelligence Index.

  • Gemini 3.1 Pro

    Google

    Intelligence 29.7 · $2 / $12

    Compare side by side

  • Kimi K2.7 Code

    Moonshot AI

    Intelligence 25.8 · $0.95 / $4

    Compare side by side

  • Qwen3.8-27B

    Alibaba

    Intelligence 33.7 · $0.50 / $3

    Compare side by side

Sources

  • Announcement (opens in a new tab)
  • Model documentation (opens in a new tab)
  • Pricing (opens in a new tab)
Yardstick

A plain reading of how today’s SI models compare. Scores are taken from each benchmark’s own leaderboard wherever one exists; anything a lab reported about its own model is marked.

Data as of Oct 8, 2026.

Explore

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Methodology & sources

Sources

  • Artificial Analysis (opens in a new tab)
  • Arena (opens in a new tab)
  • Epoch AI Benchmarking Hub (opens in a new tab)
  • ARC Prize (opens in a new tab)
  • Terminal-Bench (opens in a new tab)
  • Scale AI Labs (opens in a new tab)

Yardstick is an independent reference and is not affiliated with, sponsored by or endorsed by any lab listed. Product names and logos are trademarks of their respective owners and are used only to identify them. Benchmarks are imperfect proxies: check a model on your own task before you commit to it.

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs