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 2026-10-26

GPT-6.1 Terra

Measured on 101 benchmarks across 6 reasoning efforts.

51.3

#6 of 68 models · best at max

Reasoning efforts in this ranking

max51.3#14 of 150
xhigh45.3#25 of 150
high42.4#31 of 150
medium38.2#39 of 150
none30.5#63 of 150
low29.4#72 of 150

Strengths

  • GPT-6.1 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%42.3%#3 of 68
  2. Terminal-Bench v4-AA10%55.6%#9 of 68
  3. AA-Briefcase v1.115%1401#34 of 68
  4. AutomationBench-AA5%60.2%#22 of 68
  5. Terminal-Bench-Science-AA15%57.6%#5 of 68
  6. HLE-Diamond10%47.3%#9 of 68
  7. CritPt v2 Hard Subset10%68.0%#4 of 68
  8. AA-Omniscience v1.1 Accuracy10%47.6%#15 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%65.5%#27 of 68
  10. GDP.pdf5%28.6%#7 of 68

Bars show where GPT-6.1 Terra sits among the 68 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 68 ranked models

Cost per task

#13 cheapest of 50

$0.05at max

Time per task

#24 quickest of 49

14 minat max

Output speed

#41 fastest of 60

73 tok/sat max

Time to first token

#56 quickest of 60

3.0 minat max

Output tokens per task

#16 fewest of 53

60kat 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

$0.073 per 1M tokens at API prices$0.0037 on ChatGPT Pro 10x

98.3% cache read · 1.52% fresh input · 0.02% cache write · 0.16% output

Measured from T3 Code usage in Codex, Oct 30 to Nov 5, high confidence. One app’s users, not everyone’s. $0.099 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #41max of 24560.2%
  2. #45xhigh of 24559.9%
  3. #52high of 24558.5%
  4. #58medium of 24557.8%
  5. #66low of 24556.2%
  6. #91none of 24551.0%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #66max of 2501401
  2. #79xhigh of 2501333
  3. #94high of 2501264
  4. #102none of 2501226
  5. #106medium of 2501190
  6. #136low of 2501031

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #11max of 11668.0%
  2. #19high of 11661.5%
  3. #20xhigh of 11660.5%
  4. #28medium of 11656.5%
  5. #36low of 11650.5%
  6. #60none of 11633.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #4max of 11342.3%
  2. #13high of 11337.5%
  3. #14xhigh of 11336.9%
  4. #22medium of 11334.5%
  5. #24none of 11333.4%
  6. #44low of 11324.5%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #17max of 24328.6%
  2. #19medium of 24328.4%
  3. #20high of 24328.0%
  4. #29xhigh of 24326.6%
  5. #38low of 24325.6%
  6. #55none of 24323.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #21max of 15347.3%
  2. #28xhigh of 15342.3%
  3. #34high of 15335.4%
  4. #41medium of 15331.3%
  5. #52low of 15324.9%
  6. #90none of 15314.5%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #35xhigh of 12348.0%
  2. #36max of 12347.6%
  3. #37medium of 12347.4%
  4. #38high of 12347.3%
  5. #43low of 12345.6%
  6. #55none of 12340.7%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #36max of 12365.5%
  2. #40xhigh of 12363.2%
  3. #41high of 12363.0%
  4. #47medium of 12360.4%
  5. #53low of 12358.4%
  6. #96none of 12322.9%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #9max of 12657.6%
  2. #20xhigh of 12641.9%
  3. #28high of 12633.3%
  4. #33medium of 12624.8%
  5. #35none of 12624.3%
  6. #63low of 1267.6%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #15max of 24155.6%
  2. #27xhigh of 24146.5%
  3. #35high of 24141.9%
  4. #52medium of 24132.3%
  5. #60none of 24126.8%
  6. #85low of 24115.2%

Leader: Kimi K3.1 · 67.2%

All 101 benchmarks

show 91 more