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

Thinking Machines · released 2026-07-15

Inkling

Measured on 151 benchmarks.

12.5

#54 of 68 models · best at xhigh

Strengths

  • Inkling
  • 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%3.9%#56 of 68
  2. Terminal-Bench v4-AA10%1.0%#48 of 68
  3. AA-Briefcase v1.115%833#57 of 68
  4. AutomationBench-AA5%5.0%#58 of 68
  5. Terminal-Bench-Science-AA15%0.0%#49 of 68
  6. HLE-Diamond10%10.6%#49 of 68
  7. CritPt v2 Hard Subset10%18.0%#46 of 68
  8. AA-Omniscience v1.1 Accuracy10%39.3%#26 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%32.8%#54 of 68
  10. GDP.pdf5%12.8%#40 of 68

Bars show where Inkling sits among the 68 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 68 ranked models

Cost per task

#18 cheapest of 50

$0.12at xhigh

Time per task

#13 quickest of 49

8.7 minat xhigh

Output speed

#31 fastest of 60

98 tok/sat xhigh

Time to first token

#20 quickest of 60

2.3sat xhigh

Output tokens per task

#9 fewest of 53

51kat xhigh

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

$0.216 per 1M tokens at API prices$0.020 on Droid Max

97.0% cache read · 0.00% fresh input · 2.50% 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

245 results
  1. #184xhigh of 2455.0%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #173xhigh of 250833

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #84xhigh of 11618.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #94xhigh of 1133.9%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #126xhigh of 24312.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #104xhigh of 15310.6%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #60xhigh of 12339.3%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #89xhigh of 12332.8%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #104xhigh of 1260.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #147xhigh of 2411.0%

Leader: Kimi K3.1 · 67.2%

All 151 benchmarks

show 141 more