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

Mistral · released 2026-10-06

Mistral Large 4

Measured on 138 benchmarks across 3 reasoning efforts.

26.1

#37 of 68 models · best at high

Reasoning efforts in this ranking

high26.1#82 of 150
default25.3#85 of 150
medium23.1#95 of 150

Strengths

  • Mistral Large 4
  • 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%15.0%#39 of 68
  2. Terminal-Bench v4-AA10%24.7%#32 of 68
  3. AA-Briefcase v1.115%1348#37 of 68
  4. AutomationBench-AA5%57.8%#29 of 68
  5. Terminal-Bench-Science-AA15%4.3%#34 of 68
  6. HLE-Diamond10%17.3%#39 of 68
  7. CritPt v2 Hard Subset10%27.0%#39 of 68
  8. AA-Omniscience v1.1 Accuracy10%26.0%#50 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%71.8%#18 of 68
  10. GDP.pdf5%17.6%#30 of 68

Bars show where Mistral Large 4 sits among the 68 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 68 ranked models

Cost per task

#16 cheapest of 50

$0.1at high

Time per task

#17 quickest of 49

12 minat high

Output speed

#25 fastest of 60

111 tok/sat high

Time to first token

#23 quickest of 60

2.9sat high

Output tokens per task

#27 fewest of 53

82kat high

Time per task: Artificial Analysis · computed, not timed: output tokens per Intelligence Index task divided by output speed, without tool time. Method changed Nov 4, 2026.

Token price

$0.096 per 1M tokens at API prices$0.0046 on Mistral Vibe Pro

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

245 results
  1. #46default of 24559.9%
  2. #57high of 24557.8%
  3. #85medium of 24552.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #67default of 2501393
  2. #76high of 2501348
  3. #107medium of 2501188

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #73high of 11627.0%
  2. #78default of 11624.5%
  3. #80medium of 11622.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #70high of 11315.0%
  2. #72default of 11313.6%
  3. #73medium of 11313.3%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #84default of 24318.6%
  2. #93high of 24317.6%
  3. #104medium of 24316.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #77high of 15317.3%
  2. #86default of 15315.1%
  3. #94medium of 15313.9%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #96high of 12326.0%
  2. #97default of 12323.9%
  3. #100medium of 12322.5%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #17medium of 12375.2%
  2. #26high of 12371.8%
  3. #52default of 12358.7%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #73default of 1264.8%
  2. #76high of 1264.3%
  3. #81medium of 1263.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #61default of 24126.8%
  2. #69high of 24124.7%
  3. #71medium of 24123.2%

Leader: Kimi K3.1 · 67.2%

All 138 benchmarks

show 128 more