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 2026-09-22

Opus 5.5

Measured on 241 benchmarks across 5 reasoning efforts.

58.9

#2 of 67 models · best at max

Reasoning efforts in this ranking

max58.9#2 of 149
xhigh57.3#4 of 149
high51.7#12 of 149
medium48.0#21 of 149
low34.7#48 of 149

Strengths

  • Opus 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%46.4%#1 of 67
  2. Terminal-Bench v4-AA10%59.6%#4 of 67
  3. AA-Briefcase v1.115%1800#2 of 67
  4. AutomationBench-AA5%69.5%#7 of 67
  5. Terminal-Bench-Science-AA15%59.0%#3 of 67
  6. HLE-Diamond10%67.9%#2 of 67
  7. CritPt v2 Hard Subset10%68.0%#4 of 67
  8. AA-Omniscience v1.1 Accuracy10%65.5%#2 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%49.7%#42 of 67
  10. GDP.pdf5%26.2%#11 of 67

Bars show where Opus 5.5 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

Cost per task

#20 cheapest of 50

$0.15at max

Time per task

#39 quickest of 49

27 minat max

Output speed

#26 fastest of 59

106 tok/sat max

Time to first token

#59 quickest of 59

5.6 minat max

Output tokens per task

#50 fewest of 53

173kat 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.

API default effort: medium, per Artificial Analysis.

Token price

$0.351 per 1M tokens at API prices$0.0053 on Claude Ultra

97.9% cache read · 0.04% fresh input · 1.76% cache write · 0.33% output

Measured from T3 Code usage in Claude Code, Oct 30 to Nov 5, high confidence. One app’s users, not everyone’s. $0.394 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #8max of 24569.5%
  2. #24xhigh of 24565.0%
  3. #31high of 24563.2%
  4. #38medium of 24561.2%
  5. #84low of 24552.9%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #2max of 2501800
  2. #3xhigh of 2501760
  3. #6high of 2501682
  4. #16medium of 2501620
  5. #86low of 2501279

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #10max of 11668.0%
  2. #12xhigh of 11667.5%
  3. #23high of 11659.5%
  4. #29medium of 11654.0%
  5. #54low of 11636.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #1max of 11346.4%
  2. #2xhigh of 11343.8%
  3. #17high of 11335.9%
  4. #25medium of 11333.1%
  5. #69low of 11315.8%

Leader: this model · 46.4%

economics

GDP.pdf

243 results
  1. #15high of 24328.8%
  2. #28xhigh of 24326.6%
  3. #31max of 24326.2%
  4. #36medium of 24325.6%
  5. #37low of 24325.6%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #2max of 15267.9%
  2. #4xhigh of 15264.0%
  3. #14high of 15255.6%
  4. #18medium of 15251.4%
  5. #29low of 15241.7%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #3xhigh of 12265.5%
  2. #4max of 12265.5%
  3. #5high of 12264.8%
  4. #7medium of 12263.9%
  5. #8low of 12263.3%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #67max of 12249.7%
  2. #81high of 12236.1%
  3. #83xhigh of 12235.0%
  4. #85low of 12233.7%
  5. #87medium of 12233.1%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #4xhigh of 12661.9%
  2. #7max of 12659.0%
  3. #16high of 12649.0%
  4. #19medium of 12643.3%
  5. #34low of 12624.3%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #6max of 24159.6%
  2. #7xhigh of 24159.6%
  3. #13high of 24156.6%
  4. #19medium of 24152.5%
  5. #53low of 24131.3%

Leader: Kimi K3.1 · 67.2%

All 241 benchmarks

show 231 more