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 2026-09-29

GPT-6.1 Sol

Measured on 191 benchmarks across 5 reasoning efforts.

54.4

#4 of 61 models · best at max

Reasoning efforts in this ranking

max54.4#8 of 139
xhigh52.3#11 of 139
high50.2#16 of 139
medium46.1#23 of 139
low34.5#45 of 139

Strengths

  • GPT-6.1 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%40.6%#5 of 61
  2. Terminal-Bench v4-AA10%56.1%#8 of 61
  3. AA-Briefcase v1.115%1555#16 of 61
  4. AutomationBench-AA5%64.9%#15 of 61
  5. Terminal-Bench-Science-AA15%58.1%#4 of 61
  6. HLE-Diamond10%58.8%#4 of 61
  7. CritPt v2 Hard Subset10%68.5%#2 of 61
  8. AA-Omniscience v1.1 Accuracy10%61.8%#3 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%48.1%#39 of 61
  10. GDP.pdf5%31.0%#3 of 61

Bars show where GPT-6.1 Sol 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

#14 cheapest of 41

$0.07at max

Time per task

#24 quickest of 40

12 minat max

Output speed

#33 fastest of 52

93 tok/sat max

Time to first token

#48 quickest of 52

5.1 minat max

Output tokens per task

#16 fewest of 44

68kat max

Token price

$0.178 per 1M tokens at API prices$0.010 on ChatGPT Pro 10x

97.4% cache read · 2.18% fresh input · 0.04% cache write · 0.36% output

Measured from T3 Code usage in Codex, Oct 27 to Nov 2, high confidence. One app’s users, not everyone’s. $0.197 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #19xhigh of 24166.6%
  2. #23max of 24164.9%
  3. #25high of 24164.5%
  4. #31medium of 24162.6%
  5. #84low of 24152.6%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #28max of 2471555
  2. #39xhigh of 2471502
  3. #50high of 2471467
  4. #70medium of 2471361
  5. #117low of 2471114

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #5max of 10068.5%
  2. #6xhigh of 10068.0%
  3. #7high of 10067.5%
  4. #8medium of 10065.0%
  5. #18low of 10059.5%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #7max of 9740.6%
  2. #11xhigh of 9738.5%
  3. #15high of 9736.7%
  4. #22medium of 9733.4%
  5. #50low of 9720.2%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #3high of 24032.0%
  2. #4xhigh of 24031.8%
  3. #8max of 24031.0%
  4. #12medium of 24030.0%
  5. #24low of 24027.0%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #10max of 14258.8%
  2. #13xhigh of 14255.8%
  3. #17high of 14251.9%
  4. #22medium of 14246.0%
  5. #30low of 14238.2%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #10max of 11161.8%
  2. #13xhigh of 11161.1%
  3. #15high of 11160.4%
  4. #17medium of 11159.6%
  5. #19low of 11158.6%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #55xhigh of 11152.0%
  2. #56medium of 11151.9%
  3. #58high of 11151.0%
  4. #60low of 11150.1%
  5. #64max of 11148.1%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #8max of 11558.1%
  2. #15xhigh of 11550.5%
  3. #17high of 11546.2%
  4. #24medium of 11537.1%
  5. #48low of 11511.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #14max of 23856.1%
  2. #18xhigh of 23854.0%
  3. #23high of 23851.5%
  4. #26medium of 23848.0%
  5. #52low of 23830.8%

Leader: Kimi K3.1 · 67.2%

All 191 benchmarks

show 181 more