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 Sol

Measured on 222 benchmarks across 6 reasoning efforts.

40.6

#14 of 61 models · best at max

Reasoning efforts in this ranking

max40.6#35 of 139
xhigh35.1#43 of 139
high33.5#49 of 139
medium30.2#59 of 139
low23.3#86 of 139
none19.4#100 of 139

Strengths

  • GPT-5.6 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%29.8% est.#11 of 61
  2. Terminal-Bench v4-AA10%39.9%#15 of 61
  3. AA-Briefcase v1.115%1479#24 of 61
  4. AutomationBench-AA5%60.1%#21 of 61
  5. Terminal-Bench-Science-AA15%22.4%#14 of 61
  6. HLE-Diamond10%41.3% est.#12 of 61
  7. CritPt v2 Hard Subset10%56.0%#8 of 61
  8. AA-Omniscience v1.1 Accuracy10%56.9% est.#7 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%33.9% est.#47 of 61
  10. GDP.pdf5%27.2%#8 of 61

Bars show where GPT-5.6 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

#22 fastest of 52

130 tok/sat max

Time to first token

#42 quickest of 52

1.9 minat max

Token price

$0.524 per 1M tokens at API prices$0.014 on ChatGPT Pro 10x

97.8% cache read · 1.78% fresh input · 0.19% 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. $0.588 at the standard 97 / 2.5 / 0.5 mix.

Not measured for GPT-5.6 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. #41max of 24160.1%
  2. #68high of 24155.3%
  3. #69xhigh of 24155.3%
  4. #88medium of 24151.3%
  5. #111low of 24141.0%
  6. #147none of 24122.7%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #47max of 2471479
  2. #55xhigh of 2471436
  3. #69high of 2471369
  4. #96medium of 2471241
  5. #130low of 2471044
  6. #137none of 2471007

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #25max of 10056.0%

Leader: GPT-6 Astra · 71.5%

economics

GDP.pdf

240 results
  1. #21high of 24027.8%
  2. #22xhigh of 24027.6%
  3. #23max of 24027.2%
  4. #33medium of 24026.2%
  5. #66low of 24021.0%
  6. #111none of 24015.2%

Leader: Muse Wonder Full · 32.6%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #36max of 11522.4%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #38max of 23839.9%
  2. #68xhigh of 23824.7%
  3. #75high of 23820.7%
  4. #86medium of 23814.6%
  5. #146low of 2381.0%

Leader: Kimi K3.1 · 67.2%

All 222 benchmarks

show 216 more