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 2026-05-28

Opus 4.8

Measured on 208 benchmarks.

29.4

#31 of 98 models · best at max

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

Strengths

  • Opus 4.8
  • 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%23.8% est.#25 of 98
  2. Terminal-Bench v4-AA10%21.7%#35 of 98
  3. AA-Briefcase v1.115%1320#43 of 98
  4. AutomationBench-AA5%45.6%#50 of 98
  5. Terminal-Bench-Science-AA15%11.7% est.#22 of 98
  6. HLE-Diamond10%24.1% est.#29 of 98
  7. CritPt v2 Hard Subset10%36.1% est.#26 of 98
  8. AA-Omniscience v1.1 Accuracy10%39.6% est.#31 of 98
  9. AA-Omniscience v1.1 Non-hallucination5%46.6% est.#57 of 98
  10. GDP.pdf5%22.8%#20 of 98

Bars show where Opus 4.8 sits among the 98 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 98 ranked models

Output speed

#52 fastest of 79

82 tok/sat max

Time to first token

#61 quickest of 79

38sat max

Token price

$0.754 per 1M tokens at API prices$0.013 on Claude Ultra

97.1% cache read · 0.27% fresh input · 2.14% cache write · 0.49% output

Measured from T3 Code usage in Claude Code, Oct 30 to Nov 5, medium confidence. One app’s users, not everyone’s. $0.735 at the standard 97 / 2.5 / 0.5 mix.

Not measured for Opus 4.8: 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

245 results
  1. #109max of 24545.6%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #83max of 2501320

Leader: Sonnet 5.5 · 1813

economics

GDP.pdf

243 results
  1. #59max of 24322.8%

Leader: Muse Wonder Full · 32.6%

coding

Terminal-Bench v4-AA

241 results
  1. #74max of 24121.7%

Leader: Kimi K3.1 · 67.2%

All 208 benchmarks

show 204 more