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

Anthropic · released 2026-09-28

Sonnet 5.5

Measured on 174 benchmarks across 5 reasoning efforts.

54.6

#4 of 68 models · best at max

Reasoning efforts in this ranking

max54.6#8 of 150
xhigh49.9#18 of 150
high41.5#33 of 150
medium30.7#61 of 150
low25.6#84 of 150

Strengths

  • Sonnet 5.5
  • 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%41.7%#4 of 68
  2. Terminal-Bench v4-AA10%63.6%#3 of 68
  3. AA-Briefcase v1.115%1813#1 of 68
  4. AutomationBench-AA5%71.8%#5 of 68
  5. Terminal-Bench-Science-AA15%53.3%#6 of 68
  6. HLE-Diamond10%53.3%#7 of 68
  7. CritPt v2 Hard Subset10%59.0%#9 of 68
  8. AA-Omniscience v1.1 Accuracy10%51.5%#9 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%56.7%#37 of 68
  10. GDP.pdf5%25.8%#13 of 68

Bars show where Sonnet 5.5 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

#19 cheapest of 50

$0.15at max

Time per task

#43 quickest of 49

31 minat max

Output speed

#11 fastest of 60

151 tok/sat max

Time to first token

#59 quickest of 60

4.7 minat max

Output tokens per task

#53 fewest of 53

285kat 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

$0.194 per 1M tokens at API prices$0.0029 on Claude Ultra

97.4% cache read · 0.05% fresh input · 2.13% cache write · 0.42% output

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

245 results
  1. #6max of 24571.8%
  2. #23xhigh of 24565.5%
  3. #48high of 24559.4%
  4. #72medium of 24554.9%
  5. #95low of 24549.4%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #1max of 2501813
  2. #4xhigh of 2501742
  3. #13high of 2501634
  4. #57medium of 2501439
  5. #91low of 2501268

Leader: this model · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #24max of 11659.0%
  2. #26xhigh of 11657.5%
  3. #32high of 11651.5%
  4. #59medium of 11633.5%
  5. #75low of 11626.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #5max of 11341.7%
  2. #19xhigh of 11335.6%
  3. #39high of 11325.7%
  4. #80medium of 11311.0%
  5. #87low of 1137.1%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #35max of 24325.8%
  2. #40high of 24325.2%
  3. #42xhigh of 24324.6%
  4. #75medium of 24320.2%
  5. #106low of 24316.0%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #15max of 15353.3%
  2. #27xhigh of 15344.1%
  3. #36high of 15333.8%
  4. #57medium of 15323.8%
  5. #67low of 15320.6%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #23max of 12351.5%
  2. #25xhigh of 12350.9%
  3. #27high of 12350.3%
  4. #40low of 12346.0%
  5. #41medium of 12345.8%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #55max of 12356.7%
  2. #60low of 12352.3%
  3. #67medium of 12350.0%
  4. #79xhigh of 12338.3%
  5. #81high of 12336.4%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #11max of 12653.3%
  2. #14xhigh of 12652.4%
  3. #27high of 12634.3%
  4. #43medium of 12616.2%
  5. #53low of 12610.5%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #3max of 24163.6%
  2. #12xhigh of 24157.1%
  3. #32high of 24143.9%
  4. #56medium of 24129.8%
  5. #76low of 24120.7%

Leader: Kimi K3.1 · 67.2%

All 174 benchmarks

show 164 more