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

OpenAI · released 2026-07-30

GPT-5.6 Luna

Measured on 180 benchmarks across 6 reasoning efforts.

23.7

#41 of 67 models · best at max

Reasoning efforts in this ranking

max23.7#93 of 149
xhigh21.4#102 of 149
high19.4#108 of 149
medium14.5#122 of 149
low11.5#134 of 149
none9.4#138 of 149

Strengths

  • GPT-5.6 Luna
  • 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%17.6%#36 of 67
  2. Terminal-Bench v4-AA10%11.6%#41 of 67
  3. AA-Briefcase v1.115%1339#38 of 67
  4. AutomationBench-AA5%50.2%#39 of 67
  5. Terminal-Bench-Science-AA15%3.3%#39 of 67
  6. HLE-Diamond10%20.9%#31 of 67
  7. CritPt v2 Hard Subset10%30.5%#33 of 67
  8. AA-Omniscience v1.1 Accuracy10%39.1%#27 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%7.7%#65 of 67
  10. GDP.pdf5%24.0%#16 of 67

Bars show where GPT-5.6 Luna sits among the 67 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 67 ranked models

Cost per task

#11 cheapest of 50

$0.02at max

Time per task

#15 quickest of 49

11 minat max

Output speed

#33 fastest of 59

94 tok/sat max

Time to first token

#50 quickest of 59

1.2 minat max

Output tokens per task

#15 fewest of 53

59kat max

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

$0.029 per 1M tokens at API prices$0.0013 on ChatGPT Pro 20x

97.1% cache read · 2.25% fresh input · 0.26% cache write · 0.34% output

Measured from T3 Code usage in Codex, Oct 30 to Nov 5, medium confidence. One app’s users, not everyone’s. $0.030 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #93max of 24550.2%
  2. #111xhigh of 24542.6%
  3. #125high of 24535.6%
  4. #147medium of 24523.1%
  5. #172low of 24511.7%
  6. #185none of 2455.0%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #77max of 2501339
  2. #92xhigh of 2501267
  3. #112high of 2501170
  4. #153medium of 250933
  5. #180low of 250741
  6. #189none of 250707

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #66max of 11630.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #63max of 11317.6%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #49max of 24324.0%
  2. #52xhigh of 24323.8%
  3. #61high of 24322.2%
  4. #113medium of 24315.2%
  5. #118low of 24314.2%
  6. #175none of 2436.0%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #65max of 15220.9%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #61max of 12239.1%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #118max of 1227.7%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #80max of 1263.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #103max of 24111.6%
  2. #125xhigh of 2413.5%
  3. #134high of 2412.5%
  4. #155none of 2411.0%
  5. #166medium of 2410.5%
  6. #184low of 2410.0%

Leader: Kimi K3.1 · 67.2%

All 180 benchmarks

show 170 more