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 2026-07-24

Opus 5

Measured on 212 benchmarks across 5 reasoning efforts.

43.9

#11 of 61 models · best at max

Reasoning efforts in this ranking

max43.9#26 of 139
xhigh42.2#32 of 139
high40.8#34 of 139
medium35.3#41 of 139
low29.5#66 of 139

Strengths

  • Opus 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%29.6% est.#12 of 61
  2. Terminal-Bench v4-AA10%49.0%#12 of 61
  3. AA-Briefcase v1.115%1656#6 of 61
  4. AutomationBench-AA5%56.6%#31 of 61
  5. Terminal-Bench-Science-AA15%28.6%#12 of 61
  6. HLE-Diamond10%47.2% est.#10 of 61
  7. CritPt v2 Hard Subset10%53.5% est.#10 of 61
  8. AA-Omniscience v1.1 Accuracy10%61.0% est.#5 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%30.0% est.#51 of 61
  10. GDP.pdf5%21.6%#20 of 61

Bars show where Opus 5 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

#45 fastest of 52

54 tok/sat max

Time to first token

#38 quickest of 52

1.2 minat max

Token price

$0.725 per 1M tokens at API prices$0.013 on Claude Max 20x

96.9% cache read · 1.04% fresh input · 1.73% cache write · 0.32% output

Measured from T3 Code usage in Claude Code, Oct 27 to Nov 2, high confidence. One app’s users, not everyone’s. $0.735 at the standard 97 / 2.5 / 0.5 mix.

Not measured for Opus 5: cost per task, time per task, output tokens per task (no published API price yet).

This ranking’s benchmarks

5 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #62max of 24156.6%
  2. #72medium of 24154.3%
  3. #76high of 24153.6%
  4. #78xhigh of 24153.2%
  5. #87low of 24151.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #10max of 2471656
  2. #14xhigh of 2471630
  3. #27high of 2471558
  4. #56medium of 2471432
  5. #100low of 2471208

Leader: Sonnet 5.5 · 1814

economics

GDP.pdf

240 results
  1. #62max of 24021.6%
  2. #67xhigh of 24021.0%
  3. #76medium of 24020.0%
  4. #78high of 24019.6%
  5. #96low of 24017.2%

Leader: Muse Wonder Full · 32.6%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #31max of 11528.6%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #25max of 23849.0%
  2. #28xhigh of 23846.5%
  3. #29high of 23846.0%
  4. #43medium of 23834.3%
  5. #61low of 23826.3%

Leader: Kimi K3.1 · 67.2%

All 212 benchmarks

show 207 more