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 165 benchmarks across 6 reasoning efforts.

43.7

#12 of 61 models · best at max

Reasoning efforts in this ranking

max43.7#27 of 139
xhigh35.7#40 of 139
high34.1#48 of 139
medium28.0#72 of 139
low21.2#96 of 139
none18.5#105 of 139

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%31.7% est.#10 of 61
  2. Terminal-Bench v4-AA10%43.9%#13 of 61
  3. AA-Briefcase v1.115%1476#25 of 61
  4. AutomationBench-AA5%61.6%#18 of 61
  5. Terminal-Bench-Science-AA15%30.0%#11 of 61
  6. HLE-Diamond10%45.2%#11 of 61
  7. CritPt v2 Hard Subset10%58.0% est.#6 of 61
  8. AA-Omniscience v1.1 Accuracy10%56.8% est.#8 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%47.8% est.#40 of 61
  10. GDP.pdf5%25.2%#13 of 61

Bars show where GPT-6 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

Output speed

#17 fastest of 52

154 tok/sat max

Time to first token

#40 quickest of 52

1.7 minat max

Token price

$0.258 per 1M tokens at API prices$0.0080 on ChatGPT Pro 10x

98.0% cache read · 1.53% fresh input · 0.21% cache write · 0.26% output

Measured from T3 Code usage in Codex, Oct 27 to Nov 2, high confidence. One app’s users, not everyone’s. $0.294 at the standard 97 / 2.5 / 0.5 mix.

Not measured for GPT-6 Sol: cost per task, time per task, output tokens per task (no published API price yet).

This ranking’s benchmarks

6 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #34xhigh of 24161.7%
  2. #35max of 24161.6%
  3. #40high of 24160.1%
  4. #52medium of 24158.0%
  5. #75low of 24153.9%
  6. #127none of 24134.2%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #48max of 2471476
  2. #71xhigh of 2471358
  3. #90high of 2471266
  4. #112medium of 2471148
  5. #119none of 2471105
  6. #160low of 247885

Leader: Sonnet 5.5 · 1814

economics

GDP.pdf

240 results
  1. #39max of 24025.2%
  2. #42xhigh of 24024.6%
  3. #43high of 24024.4%
  4. #44low of 24024.2%
  5. #49medium of 24023.8%
  6. #100none of 24017.0%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #23max of 14245.2%
  2. #101none of 1429.5%

Leader: Gemini 4 Carbon · 69.1%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #29max of 11530.0%
  2. #40xhigh of 11517.6%
  3. #41high of 11517.1%
  4. #58medium of 1158.6%
  5. #66none of 1155.7%
  6. #78low of 1153.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #32max of 23843.9%
  2. #53xhigh of 23830.3%
  3. #62high of 23826.3%
  4. #79medium of 23818.7%
  5. #92none of 23813.1%
  6. #106low of 2389.1%

Leader: Kimi K3.1 · 67.2%

All 165 benchmarks

show 159 more