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 2026-09-03

GPT-6 Astra

Measured on 252 benchmarks across 5 reasoning efforts.

56.9

#3 of 67 models · best at max

Reasoning efforts in this ranking

max56.9#5 of 149
xhigh55.3#6 of 149
high54.8#7 of 149
medium51.6#13 of 149
low43.3#29 of 149

Strengths

  • GPT-6 Astra
  • 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%42.4%#2 of 67
  2. Terminal-Bench v4-AA10%59.1%#5 of 67
  3. AA-Briefcase v1.115%1569#16 of 67
  4. AutomationBench-AA5%68.5%#9 of 67
  5. Terminal-Bench-Science-AA15%63.3%#2 of 67
  6. HLE-Diamond10%63.8%#3 of 67
  7. CritPt v2 Hard Subset10%70.5%#1 of 67
  8. AA-Omniscience v1.1 Accuracy10%61.6%#4 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%50.2%#41 of 67
  10. GDP.pdf5%31.0%#3 of 67

Bars show where GPT-6 Astra 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

#28 cheapest of 50

$0.27at max

Time per task

#33 quickest of 49

20 minat max

Output speed

#55 fastest of 59

43 tok/sat max

Time to first token

#57 quickest of 59

4.0 minat max

Output tokens per task

#12 fewest of 53

52kat 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.

API default effort: medium, per Artificial Analysis.

Token price

$1.421 per 1M tokens at API prices$0.061 on ChatGPT Pro 10x

97.0% cache read · 2.60% fresh input · 0.04% cache write · 0.37% output

Measured from T3 Code usage in Codex, Oct 30 to Nov 5, high confidence. One app’s users, not everyone’s. $1.470 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #11max of 24568.5%
  2. #15xhigh of 24567.2%
  3. #19high of 24566.6%
  4. #26medium of 24564.6%
  5. #50low of 24559.1%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #26max of 2501569
  2. #30xhigh of 2501544
  3. #39high of 2501505
  4. #53medium of 2501461
  5. #95low of 2501256

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #1medium of 11672.0%
  2. #2high of 11671.5%
  3. #3xhigh of 11671.0%
  4. #4max of 11670.5%
  5. #16low of 11663.0%

Leader: this model · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #3max of 11342.4%
  2. #6xhigh of 11341.4%
  3. #9high of 11340.1%
  4. #16medium of 11336.6%
  5. #38low of 11326.2%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #2xhigh of 24332.2%
  2. #6max of 24331.0%
  3. #7high of 24331.0%
  4. #10medium of 24330.4%
  5. #11low of 24330.4%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #5max of 15263.8%
  2. #7xhigh of 15261.5%
  3. #9high of 15259.3%
  4. #16medium of 15252.7%
  5. #24low of 15245.1%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #11max of 12261.6%
  2. #12high of 12261.1%
  3. #14xhigh of 12261.0%
  4. #17medium of 12259.6%
  5. #21low of 12258.6%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #53high of 12257.5%
  2. #55low of 12255.8%
  3. #56xhigh of 12255.4%
  4. #57medium of 12254.8%
  5. #64max of 12250.2%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #2max of 12663.3%
  2. #6high of 12659.5%
  3. #10xhigh of 12654.8%
  4. #12medium of 12653.3%
  5. #25low of 12637.1%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #8xhigh of 24159.6%
  2. #9max of 24159.1%
  3. #17high of 24154.0%
  4. #24medium of 24149.5%
  5. #34low of 24141.9%

Leader: Kimi K3.1 · 67.2%

All 252 benchmarks

show 242 more