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 2026-09-21

Grok 4.7

Measured on 213 benchmarks across 3 reasoning efforts.

35.3

#18 of 67 models · best at xhigh

Reasoning efforts in this ranking

xhigh35.3#44 of 149
high35.1#45 of 149
low31.0#58 of 149

Strengths

  • Grok 4.7
  • 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%28.7%#14 of 67
  2. Terminal-Bench v4-AA10%25.8%#29 of 67
  3. AA-Briefcase v1.115%1637#8 of 67
  4. AutomationBench-AA5%65.6%#16 of 67
  5. Terminal-Bench-Science-AA15%11.4%#21 of 67
  6. HLE-Diamond10%23.2%#28 of 67
  7. CritPt v2 Hard Subset10%33.5%#28 of 67
  8. AA-Omniscience v1.1 Accuracy10%42.7%#20 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%80.0%#6 of 67
  10. GDP.pdf5%20.0%#27 of 67

Bars show where Grok 4.7 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

#37 cheapest of 50

$0.72at xhigh

Time per task

#37 quickest of 49

24 minat xhigh

Output speed

#42 fastest of 59

71 tok/sat xhigh

Time to first token

#45 quickest of 59

55sat xhigh

Output tokens per task

#35 fewest of 53

105kat 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.

API default effort: high, per Artificial Analysis.

Token price

$0.565 per 1M tokens at API prices$0.052 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. #22xhigh of 24565.6%
  2. #29high of 24563.5%
  3. #62low of 24556.7%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #12xhigh of 2501637
  2. #14high of 2501629
  3. #43low of 2501493

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #46low of 11643.5%
  2. #52high of 11637.0%
  3. #57xhigh of 11633.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #33xhigh of 11328.7%
  2. #36high of 11327.8%
  3. #52low of 11321.8%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #54high of 24323.2%
  2. #66low of 24321.4%
  3. #78xhigh of 24320.0%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #59high of 15223.6%
  2. #60xhigh of 15223.2%
  3. #72low of 15218.5%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #42low of 12245.7%
  2. #47xhigh of 12242.7%
  3. #51high of 12241.8%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #9xhigh of 12280.0%
  2. #10high of 12279.8%
  3. #32low of 12266.2%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #48xhigh of 12611.4%
  2. #56high of 1269.5%
  3. #71low of 1264.8%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #65xhigh of 24125.8%
  2. #68high of 24124.7%
  3. #84low of 24116.2%

Leader: Kimi K3.1 · 67.2%

All 213 benchmarks

show 203 more