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 2026-06-30

Sonnet 5

Measured on 169 benchmarks across 5 reasoning efforts.

25.1

#41 of 94 models · best at max

includes estimates: 35% of the mix is measured for this model

Reasoning efforts in this ranking

max25.1#91 of 180
xhigh20.0#110 of 180
high17.7#126 of 180
medium15.6#131 of 180
low13.1#145 of 180

Strengths

  • Sonnet 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%15.9% est.#40 of 94
  2. Terminal-Bench v4-AA10%14.1%#36 of 94
  3. AA-Briefcase v1.115%1357#34 of 94
  4. AutomationBench-AA5%36.5%#52 of 94
  5. Terminal-Bench-Science-AA15%5.6% est.#34 of 94
  6. HLE-Diamond10%19.5% est.#38 of 94
  7. CritPt v2 Hard Subset10%32.4% est.#32 of 94
  8. AA-Omniscience v1.1 Accuracy10%33.7% est.#47 of 94
  9. AA-Omniscience v1.1 Non-hallucination5%58.8% est.#36 of 94
  10. GDP.pdf5%13.2%#45 of 94

Bars show where Sonnet 5 sits among the 94 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 94 ranked models

Output speed

#50 fastest of 74

84 tok/sat max

Time to first token

#68 quickest of 74

2.7 minat max

Token price

$0.274 per 1M tokens at API prices$0.0047 on Claude Max 20x

97.6% cache read · 0.31% fresh input · 1.83% cache write · 0.27% output

Measured from T3 Code usage in Claude Code, Oct 27 to Nov 2, medium confidence. One app’s users, not everyone’s. $0.294 at the standard 97 / 2.5 / 0.5 mix.

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

This ranking’s benchmarks

4 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #118max of 24136.5%
  2. #126xhigh of 24134.5%
  3. #130high of 24132.1%
  4. #138medium of 24127.9%
  5. #153low of 24119.9%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #72max of 2471357
  2. #86xhigh of 2471272
  3. #108high of 2471177
  4. #129medium of 2471058
  5. #152low of 247927

Leader: Sonnet 5.5 · 1814

economics

GDP.pdf

240 results
  1. #120max of 24013.2%
  2. #127xhigh of 24012.6%
  3. #132medium of 24011.6%
  4. #151low of 2409.4%
  5. #152high of 2409.4%

Leader: Muse Wonder Full · 32.6%

coding

Terminal-Bench v4-AA

238 results
  1. #89max of 23814.1%
  2. #112xhigh of 2387.1%
  3. #119high of 2385.1%
  4. #130low of 2382.5%
  5. #136medium of 2382.0%

Leader: Kimi K3.1 · 67.2%

All 169 benchmarks

show 165 more