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

Other · released 2026-11-07

Agnes 2.5 Pro Theta

Measured on 31 benchmarks.

24.0

#42 of 69 models

Strengths

  • Agnes 2.5 Pro Theta
  • Fable 5.2 (#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%16.6%#40 of 69
  2. Terminal-Bench v4-AA10%10.1%#44 of 69
  3. AA-Briefcase v1.115%1496#25 of 69
  4. AutomationBench-AA5%48.8%#42 of 69
  5. Terminal-Bench-Science-AA15%3.8%#40 of 69
  6. HLE-Diamond10%16.8%#42 of 69
  7. CritPt v2 Hard Subset10%26.0%#42 of 69
  8. AA-Omniscience v1.1 Accuracy10%21.3%#52 of 69
  9. AA-Omniscience v1.1 Non-hallucination5%58.6%#37 of 69
  10. GDP.pdf5%14.2%#39 of 69

Bars show where Agnes 2.5 Pro Theta sits among the 69 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 69 ranked models

Cost per task

#37 cheapest of 51

$0.57

Time per task

#34 quickest of 49

24 min

Output speed

#9 fastest of 59

194 tok/s

Time to first token

#23 quickest of 59

2.6s

Output tokens per task

#54 fewest of 55

278k

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

$0.014 per 1M tokens at API prices

97.0% cache read · 2.50% fresh input · 0.00% cache write · 0.50% output

Assumed mix: no measured T3 Code usage for this model.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

254 results
  1. #105default of 25448.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

259 results
  1. #50default of 2591496

Leader: Sonnet 5.5 · 1816

reasoning

CritPt v2 Hard Subset

126 results
  1. #83default of 12626.0%

Leader: Fable 5.2 · 76.5%

coding

FrontierCode 2.0-AA

123 results
  1. #74default of 12316.6%

Leader: Fable 5.2 · 49.1%

economics

GDP.pdf

252 results
  1. #125default of 25214.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

162 results
  1. #87default of 16216.8%

Leader: Fable 5.2 · 80.2%

knowledge

AA-Omniscience v1.1 Accuracy

134 results
  1. #111default of 13421.3%

Leader: Fable 5.2 · 79.1%

knowledge

AA-Omniscience v1.1 Non-hallucination

134 results
  1. #56default of 13458.6%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

135 results
  1. #84default of 1353.8%

Leader: Fable 5.2 · 73.3%

coding

Terminal-Bench v4-AA

250 results
  1. #113default of 25010.1%

Leader: Kimi K3.1 · 67.2%

All 31 benchmarks

show 21 more