priorsBuilder
Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

MiniMax · released 2026-10-19

MiniMax M3.1

Measured on 77 benchmarks.

28.9

#27 of 61 models · best at max

Strengths

  • MiniMax M3.1
  • Gemini 4 Carbon (#1)
  • Field median
bestField medianFrontierCode 2.0-…Terminal-Bench v4…AA-Briefcase v1.1AutomationBench-AATerminal-Bench-Sc…HLE-DiamondCritPt v2 Hard Su…AA-Omniscience v1…AA-Omniscience v1…GDP.pdf
  1. FrontierCode 2.0-AA15%20.8%#27 of 61
  2. Terminal-Bench v4-AA10%25.8%#27 of 61
  3. AA-Briefcase v1.115%1475#26 of 61
  4. AutomationBench-AA5%72.5%#4 of 61
  5. Terminal-Bench-Science-AA15%3.3%#35 of 61
  6. HLE-Diamond10%28.1%#19 of 61
  7. CritPt v2 Hard Subset10%31.0%#29 of 61
  8. AA-Omniscience v1.1 Accuracy10%45.1%#16 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%6.3%#60 of 61
  10. GDP.pdf5%20.8%#22 of 61

Bars show where MiniMax M3.1 sits among the 61 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 61 ranked models

Cost per task

#27 cheapest of 41

$0.49at max

Time per task

#27 quickest of 40

16 minat max

Output speed

#25 fastest of 52

120 tok/sat max

Time to first token

#8 quickest of 52

0.9sat max

Output tokens per task

#37 fewest of 44

138kat max

Token price

$0.021 per 1M tokens at API prices

97.0% cache read · 2.50% fresh input · 0.00% cache write · 0.50% output

Assumed mix: no measured T3 Code usage for this model.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #5max of 24172.5%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #49max of 2471475

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #55max of 10031.0%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #49max of 9720.8%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #69max of 24020.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #44max of 14228.1%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #41max of 11145.1%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #108max of 1116.3%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #76max of 1153.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #64max of 23825.8%

Leader: Kimi K3.1 · 67.2%

All 77 benchmarks

show 67 more