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 224 benchmarks across 6 reasoning efforts.

41.2

#14 of 67 models · best at max

Reasoning efforts in this ranking

max41.2#34 of 149
xhigh35.6#43 of 149
high33.5#51 of 149
medium30.5#64 of 149
low23.8#92 of 149
none19.8#107 of 149

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%30.6% est.#13 of 67
  2. Terminal-Bench v4-AA10%39.9%#15 of 67
  3. AA-Briefcase v1.115%1479#26 of 67
  4. AutomationBench-AA5%60.1%#23 of 67
  5. Terminal-Bench-Science-AA15%22.4%#14 of 67
  6. HLE-Diamond10%42.4% est.#12 of 67
  7. CritPt v2 Hard Subset10%60.0%#7 of 67
  8. AA-Omniscience v1.1 Accuracy10%54.5% est.#8 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%38.1% est.#50 of 67
  10. GDP.pdf5%27.2%#9 of 67

Bars show where GPT-5.6 Sol 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

Output speed

#28 fastest of 59

101 tok/sat max

Time to first token

#49 quickest of 59

1.2 minat max

Token price

$0.530 per 1M tokens at API prices$0.015 on ChatGPT Pro 10x

97.6% cache read · 2.01% fresh input · 0.09% cache write · 0.27% output

Measured from T3 Code usage in Codex, Oct 30 to Nov 5, 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

245 results
  1. #43max of 24560.1%
  2. #70high of 24555.3%
  3. #71xhigh of 24555.3%
  4. #90medium of 24551.3%
  5. #114low of 24541.0%
  6. #150none of 24522.7%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #47max of 2501479
  2. #58xhigh of 2501435
  3. #71high of 2501368
  4. #99medium of 2501242
  5. #133low of 2501044
  6. #140none of 2501007

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #22max of 11660.0%

Leader: GPT-6 Astra · 72.0%

economics

GDP.pdf

243 results
  1. #22high of 24327.8%
  2. #23xhigh of 24327.6%
  3. #24max of 24327.2%
  4. #34medium of 24326.2%
  5. #69low of 24321.0%
  6. #114none of 24315.2%

Leader: Muse Wonder Full · 32.6%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #36max of 12622.4%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #38max of 24139.9%
  2. #70xhigh of 24124.7%
  3. #77high of 24120.7%
  4. #88medium of 24114.6%
  5. #149low of 2411.0%

Leader: Kimi K3.1 · 67.2%

All 224 benchmarks

show 218 more