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 2026-09-22

GPT-6 Luna

Measured on 175 benchmarks across 6 reasoning efforts.

27.8

#30 of 61 models · best at max

Reasoning efforts in this ranking

max27.8#74 of 139
xhigh23.3#87 of 139
high21.4#95 of 139
medium18.3#106 of 139
low9.7#128 of 139
none9.4#129 of 139

Strengths

  • GPT-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%25.2%#19 of 61
  2. Terminal-Bench v4-AA10%12.6%#35 of 61
  3. AA-Briefcase v1.115%1337#35 of 61
  4. AutomationBench-AA5%53.2%#34 of 61
  5. Terminal-Bench-Science-AA15%8.6%#24 of 61
  6. HLE-Diamond10%22.2%#27 of 61
  7. CritPt v2 Hard Subset10%41.5%#17 of 61
  8. AA-Omniscience v1.1 Accuracy10%39.6%#23 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%20.7%#54 of 61
  10. GDP.pdf5%22.8%#16 of 61

Bars show where GPT-6 Luna 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

#11 cheapest of 41

$0.01at max

Time per task

#18 quickest of 40

11 minat max

Output speed

#26 fastest of 52

117 tok/sat max

Time to first token

#43 quickest of 52

2.0 minat max

Output tokens per task

#18 fewest of 44

75kat max

Token price

$0.015 per 1M tokens at API prices$0.0011 on ChatGPT Pro 10x

96.7% cache read · 2.71% fresh input · 0.11% cache write · 0.53% output

Measured from T3 Code usage in Codex, Oct 27 to Nov 2, high confidence. One app’s users, not everyone’s. $0.015 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #79max of 24153.2%
  2. #99high of 24147.8%
  3. #101xhigh of 24147.8%
  4. #113medium of 24140.5%
  5. #168low of 24112.0%
  6. #171none of 2419.1%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #75max of 2471337
  2. #97xhigh of 2471235
  3. #105high of 2471187
  4. #120medium of 2471096
  5. #158none of 247902
  6. #178low of 247740

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #41max of 10041.5%
  2. #46xhigh of 10035.5%
  3. #56high of 10030.5%
  4. #66medium of 10026.0%
  5. #83low of 1009.5%
  6. #87none of 1004.5%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #38max of 9725.2%
  2. #52high of 9718.6%
  3. #53xhigh of 9718.4%
  4. #65medium of 9712.8%
  5. #86low of 972.2%
  6. #87none of 971.6%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #56max of 24022.8%
  2. #83xhigh of 24018.6%
  3. #87high of 24018.2%
  4. #116medium of 24013.8%
  5. #154low of 2409.0%
  6. #173none of 2405.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #57max of 14222.2%
  2. #65xhigh of 14218.9%
  3. #76high of 14215.6%
  4. #80medium of 14215.1%
  5. #99low of 14210.2%
  6. #114none of 1426.3%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #54max of 11139.6%
  2. #57high of 11139.0%
  3. #59medium of 11138.7%
  4. #60xhigh of 11138.6%
  5. #67low of 11136.1%
  6. #80none of 11130.1%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #89max of 11120.7%
  2. #90none of 11120.0%
  3. #93xhigh of 11116.0%
  4. #95low of 11115.2%
  5. #96high of 11115.1%
  6. #97medium of 11114.7%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #57max of 1158.6%
  2. #67xhigh of 1155.2%
  3. #80high of 1152.9%
  4. #85medium of 1151.4%
  5. #89low of 1151.0%
  6. #90none of 1151.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #93max of 23812.6%
  2. #109xhigh of 2388.1%
  3. #120high of 2384.5%
  4. #128medium of 2382.5%
  5. #138none of 2381.5%
  6. #171low of 2380.0%

Leader: Kimi K3.1 · 67.2%

All 175 benchmarks

show 165 more