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

Moonshot · released 2026-07-16

Kimi K3

Measured on 243 benchmarks across 2 reasoning efforts.

30.0

#27 of 68 models · best at max

Reasoning efforts in this ranking

max30.0#68 of 150
low17.4#117 of 150

Strengths

  • Kimi K3
  • 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%10.9% est.#41 of 68
  2. Terminal-Bench v4-AA10%12.6%#39 of 68
  3. AA-Briefcase v1.115%1497#23 of 68
  4. AutomationBench-AA5%58.3%#27 of 68
  5. Terminal-Bench-Science-AA15%8.1%#27 of 68
  6. HLE-Diamond10%26.9%#23 of 68
  7. CritPt v2 Hard Subset10%40.5%#21 of 68
  8. AA-Omniscience v1.1 Accuracy10%42.4% est.#7 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%23.4% est.#55 of 68
  10. GDP.pdf5%22.0%#20 of 68

Bars show where Kimi K3 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

#24 cheapest of 50

$0.22at low

Time per task

#30 quickest of 49

18 minat low

Output speed

#58 fastest of 60

39 tok/sat max

Time to first token

#36 quickest of 60

7.0sat max

Output tokens per task

#8 fewest of 53

40kat low

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

$0.441 per 1M tokens at API prices$0.040 on Kimi Pro

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

245 results
  1. #53max of 24558.3%
  2. #96low of 24549.3%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #42max of 2501497
  2. #144low of 250985

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #48max of 11640.5%
  2. #96low of 1165.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #81low of 11310.9%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #62max of 24322.0%
  2. #88low of 24318.6%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #49max of 15326.9%
  2. #93low of 15314.0%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #48low of 12342.4%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #95low of 12323.4%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #62max of 1268.1%
  2. #92low of 1261.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #98low of 24112.6%
  2. #100max of 24112.6%

Leader: Kimi K3.1 · 67.2%

All 243 benchmarks

show 233 more