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 Sol

Measured on 183 benchmarks across 6 reasoning efforts.

44.1

#11 of 67 models · best at max

Reasoning efforts in this ranking

max44.1#26 of 149
xhigh38.9#37 of 149
high37.0#40 of 149
medium30.2#65 of 149
low24.8#90 of 149
none22.5#99 of 149

Strengths

  • GPT-6 Sol
  • 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%35.6%#9 of 67
  2. Terminal-Bench v4-AA10%43.9%#13 of 67
  3. AA-Briefcase v1.115%1476#27 of 67
  4. AutomationBench-AA5%61.6%#20 of 67
  5. Terminal-Bench-Science-AA15%30.0%#11 of 67
  6. HLE-Diamond10%45.2%#10 of 67
  7. CritPt v2 Hard Subset10%66.5%#6 of 67
  8. AA-Omniscience v1.1 Accuracy10%51.1%#10 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%39.2%#49 of 67
  10. GDP.pdf5%25.2%#14 of 67

Bars show where GPT-6 Sol 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

#15 cheapest of 50

$0.08at max

Time per task

#12 quickest of 49

8.1 minat max

Output speed

#24 fastest of 59

111 tok/sat max

Time to first token

#47 quickest of 59

1.1 minat max

Output tokens per task

#13 fewest of 53

54kat 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

$0.262 per 1M tokens at API prices$0.0081 on ChatGPT Pro 10x

97.8% cache read · 1.77% fresh input · 0.19% cache write · 0.26% output

Measured from T3 Code usage in Codex, Oct 30 to Nov 5, high confidence. One app’s users, not everyone’s. $0.294 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #36xhigh of 24561.7%
  2. #37max of 24561.6%
  3. #42high of 24560.1%
  4. #54medium of 24558.0%
  5. #77low of 24553.9%
  6. #130none of 24534.2%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #50max of 2501476
  2. #74xhigh of 2501359
  3. #93high of 2501266
  4. #115medium of 2501149
  5. #122none of 2501106
  6. #163low of 250886

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #14max of 11666.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #20max of 11335.6%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #39max of 24325.2%
  2. #44xhigh of 24324.6%
  3. #45high of 24324.4%
  4. #46low of 24324.2%
  5. #51medium of 24323.8%
  6. #103none of 24317.0%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #23max of 15245.2%
  2. #107none of 1529.5%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #24max of 12251.1%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #76max of 12239.2%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #29max of 12630.0%
  2. #41xhigh of 12617.6%
  3. #42high of 12617.1%
  4. #60medium of 1268.6%
  5. #69none of 1265.7%
  6. #82low of 1263.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #31max of 24143.9%
  2. #55xhigh of 24130.3%
  3. #64high of 24126.3%
  4. #81medium of 24118.7%
  5. #95none of 24113.1%
  6. #109low of 2419.1%

Leader: Kimi K3.1 · 67.2%

All 183 benchmarks

show 173 more