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 131 benchmarks across 3 reasoning efforts.

26.1

#34 of 63 models · best at high

Reasoning efforts in this ranking

high26.1#80 of 146
default25.3#83 of 146
medium23.1#93 of 146

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%#36 of 63
  2. Terminal-Bench v4-AA10%24.7%#30 of 63
  3. AA-Briefcase v1.115%1348#34 of 63
  4. AutomationBench-AA5%57.8%#27 of 63
  5. Terminal-Bench-Science-AA15%4.3%#32 of 63
  6. HLE-Diamond10%17.3%#35 of 63
  7. CritPt v2 Hard Subset10%27.0%#36 of 63
  8. AA-Omniscience v1.1 Accuracy10%26.0%#47 of 63
  9. AA-Omniscience v1.1 Non-hallucination5%71.8%#14 of 63
  10. GDP.pdf5%17.6%#27 of 63

Bars show where Mistral Large 4 sits among the 63 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 63 ranked models

Cost per task

#11 cheapest of 44

$0.05at high

Time per task

#27 quickest of 43

19 min

Output speed

#17 fastest of 54

120 tok/s

Time to first token

#17 quickest of 54

2.3s

Output tokens per task

#23 fewest of 47

82kat high

Token price

$0.191 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

241 results
  1. #44default of 24159.9%
  2. #55high of 24157.8%
  3. #83medium of 24152.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #65default of 2471391
  2. #73high of 2471348
  3. #104medium of 2471188

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

111 results
  1. #70high of 11127.0%
  2. #75default of 11124.5%
  3. #77medium of 11122.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

108 results
  1. #68high of 10815.0%
  2. #70default of 10813.6%
  3. #71medium of 10813.3%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #81default of 24018.6%
  2. #90high of 24017.6%
  3. #101medium of 24016.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

145 results
  1. #71high of 14517.3%
  2. #80default of 14515.1%
  3. #88medium of 14513.9%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

117 results
  1. #92high of 11726.0%
  2. #93default of 11723.9%
  3. #96medium of 11722.5%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

117 results
  1. #15medium of 11775.2%
  2. #22high of 11771.8%
  3. #48default of 11758.7%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

120 results
  1. #70default of 1204.8%
  2. #73high of 1204.3%
  3. #77medium of 1203.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #59default of 23826.8%
  2. #67high of 23824.7%
  3. #69medium of 23823.2%

Leader: Kimi K3.1 · 67.2%

All 131 benchmarks

show 121 more