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

Google · released 2026-10-28

Gemini 4 Carbon

Measured on 69 benchmarks across 3 reasoning efforts.

60.0

#1 of 68 models · best at high

Reasoning efforts in this ranking

high60.0#1 of 150
medium58.3#3 of 150
low54.2#10 of 150

Strengths

  • Gemini 4 Carbon
  • 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%40.6%#6 of 68
  2. Terminal-Bench v4-AA10%65.2%#2 of 68
  3. AA-Briefcase v1.115%1611#9 of 68
  4. AutomationBench-AA5%77.8%#1 of 68
  5. Terminal-Bench-Science-AA15%64.8%#1 of 68
  6. HLE-Diamond10%69.1%#1 of 68
  7. CritPt v2 Hard Subset10%69.0%#3 of 68
  8. AA-Omniscience v1.1 Accuracy10%58.3%#6 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%88.6%#2 of 68
  10. GDP.pdf5%28.4%#8 of 68

Bars show where Gemini 4 Carbon 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

#46 cheapest of 50

$2.8at high

Time per task

#41 quickest of 49

30 minat high

Output speed

#45 fastest of 60

68 tok/sat high

Time to first token

#49 quickest of 60

1.2 minat high

Output tokens per task

#42 fewest of 53

123kat high

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: medium, per Artificial Analysis.

Token price

$0.850 per 1M tokens at API prices$0.303 on Google AI Pro (assumed same as Argon)

85.0% cache read · 14.5% 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. #1high of 24577.8%
  2. #2medium of 24577.6%
  3. #30low of 24563.5%

Leader: this model · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #17high of 2501611
  2. #20medium of 2501602
  3. #27low of 2501567

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #7high of 11669.0%
  2. #8medium of 11669.0%
  3. #15low of 11665.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #8high of 11340.6%
  2. #10medium of 11339.5%
  3. #31low of 11329.6%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #13medium of 24329.6%
  2. #16low of 24328.6%
  3. #18high of 24328.4%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #1high of 15369.1%
  2. #3medium of 15367.4%
  3. #6low of 15361.9%

Leader: this model · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #22high of 12358.3%
  2. #30low of 12349.2%
  3. #31medium of 12348.9%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #1medium of 12395.8%
  2. #3high of 12388.6%
  3. #8low of 12380.2%

Leader: this model · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #1high of 12664.8%
  2. #3medium of 12662.4%
  3. #5low of 12661.9%

Leader: this model · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #2high of 24165.2%
  2. #4low of 24162.6%
  3. #5medium of 24160.6%

Leader: Kimi K3.1 · 67.2%

All 69 benchmarks

show 59 more