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 2026-07-09

GPT-5.6 Terra

Measured on 191 benchmarks across 6 reasoning efforts.

32.3

#22 of 67 models · best at max

Reasoning efforts in this ranking

max32.3#54 of 149
xhigh28.0#76 of 149
high24.8#89 of 149
medium21.6#100 of 149
low20.4#105 of 149
none15.7#119 of 149

Strengths

  • GPT-5.6 Terra
  • 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%23.9%#23 of 67
  2. Terminal-Bench v4-AA10%35.4%#19 of 67
  3. AA-Briefcase v1.115%1333#40 of 67
  4. AutomationBench-AA5%59.6%#25 of 67
  5. Terminal-Bench-Science-AA15%13.8%#17 of 67
  6. HLE-Diamond10%28.8%#20 of 67
  7. CritPt v2 Hard Subset10%50.5%#13 of 67
  8. AA-Omniscience v1.1 Accuracy10%42.3%#21 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%10.6%#63 of 67
  10. GDP.pdf5%24.0%#16 of 67

Bars show where GPT-5.6 Terra 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

#17 cheapest of 50

$0.1at max

Time per task

#16 quickest of 49

11 minat max

Output speed

#30 fastest of 59

100 tok/sat max

Time to first token

#51 quickest of 59

1.6 minat max

Output tokens per task

#19 fewest of 53

66kat 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

$0.332 per 1M tokens at API prices$0.0092 on ChatGPT Pro 10x

95.2% cache read · 3.40% fresh input · 1.04% cache write · 0.40% output

Measured from T3 Code usage in Codex, Oct 30 to Nov 5, medium confidence. One app’s users, not everyone’s. $0.304 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #47max of 24559.6%
  2. #106xhigh of 24547.1%
  3. #113high of 24542.0%
  4. #132medium of 24533.5%
  5. #135low of 24529.1%
  6. #169none of 24512.5%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #80max of 2501333
  2. #81xhigh of 2501330
  3. #105high of 2501202
  4. #135medium of 2501039
  5. #137low of 2501015
  6. #151none of 250946

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #35max of 11650.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #46max of 11323.9%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #43xhigh of 24324.6%
  2. #48max of 24324.0%
  3. #73high of 24320.8%
  4. #94low of 24317.6%
  5. #101medium of 24317.0%
  6. #143none of 24311.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #46max of 15228.8%
  2. #53xhigh of 15224.7%
  3. #64high of 15221.0%
  4. #80medium of 15216.1%
  5. #91low of 15214.1%
  6. #134none of 1524.8%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #49max of 12242.3%
  2. #52xhigh of 12241.3%
  3. #53high of 12241.2%
  4. #56medium of 12240.5%
  5. #57low of 12239.8%
  6. #78none of 12232.6%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #112max of 12210.6%
  2. #113xhigh of 1229.9%
  3. #114high of 1229.0%
  4. #115medium of 1228.7%
  5. #116low of 1228.7%
  6. #122none of 1224.4%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #44max of 12613.8%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #42max of 24135.4%
  2. #107xhigh of 24110.1%
  3. #144high of 2411.5%
  4. #145low of 2411.5%
  5. #151medium of 2411.0%
  6. #167none of 2410.5%

Leader: Kimi K3.1 · 67.2%

All 191 benchmarks

show 181 more