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

xAI · released 2026-08-12

Grok 4.6

Measured on 196 benchmarks across 4 reasoning efforts.

31.8

#23 of 67 models · best at high

Reasoning efforts in this ranking

high31.8#56 of 149
xhigh30.9#59 of 149
medium30.1#67 of 149
low24.9#87 of 149

Strengths

  • Grok 4.6
  • 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%22.3% est.#26 of 67
  2. Terminal-Bench v4-AA10%21.2%#34 of 67
  3. AA-Briefcase v1.115%1528#18 of 67
  4. AutomationBench-AA5%66.7%#13 of 67
  5. Terminal-Bench-Science-AA15%6.2%#28 of 67
  6. HLE-Diamond10%21.8% est.#30 of 67
  7. CritPt v2 Hard Subset10%35.2% est.#24 of 67
  8. AA-Omniscience v1.1 Accuracy10%46.2% est.#16 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%63.7% est.#29 of 67
  10. GDP.pdf5%17.0%#32 of 67

Bars show where Grok 4.6 sits among the 67 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 67 ranked models

Cost per task

#33 cheapest of 50

$0.48at xhigh

Time per task

#25 quickest of 49

14 minat xhigh

Output speed

#41 fastest of 59

72 tok/sat high

Time to first token

#42 quickest of 59

34sat high

Output tokens per task

#14 fewest of 53

58kat 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

$0.565 per 1M tokens at API prices$0.058 on SuperGrok Heavy

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. #16xhigh of 24567.0%
  2. #17high of 24566.7%
  3. #32medium of 24563.2%
  4. #79low of 24553.4%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #31xhigh of 2501541
  2. #33high of 2501528
  3. #49medium of 2501478
  4. #85low of 2501285

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #49xhigh of 11640.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #57xhigh of 11319.8%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #91medium of 24317.8%
  2. #98xhigh of 24317.2%
  3. #102high of 24317.0%
  4. #107low of 24315.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #62xhigh of 15221.5%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #39xhigh of 12246.2%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #47xhigh of 12260.3%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #65high of 1266.2%
  2. #83xhigh of 1262.9%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #75high of 24121.2%
  2. #82xhigh of 24117.2%
  3. #94medium of 24113.1%
  4. #129low of 2413.0%

Leader: Kimi K3.1 · 67.2%

All 196 benchmarks

show 186 more