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

Tencent · released 2026-11-03

Hy4

Measured on 41 benchmarks.

34.6

#19 of 68 models

Strengths

  • Hy4
  • 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%31.4%#11 of 68
  2. Terminal-Bench v4-AA10%37.4%#18 of 68
  3. AA-Briefcase v1.115%1447#30 of 68
  4. AutomationBench-AA5%65.6%#15 of 68
  5. Terminal-Bench-Science-AA15%12.9%#18 of 68
  6. HLE-Diamond10%32.7%#18 of 68
  7. CritPt v2 Hard Subset10%39.0%#22 of 68
  8. AA-Omniscience v1.1 Accuracy10%50.0%#12 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%10.9%#63 of 68
  10. GDP.pdf5%21.6%#22 of 68

Bars show where Hy4 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

#30 cheapest of 50

$0.3

Time per task

#26 quickest of 49

14 min

Output speed

#34 fastest of 60

94 tok/s

Time to first token

#13 quickest of 60

1.9s

Output tokens per task

#25 fewest of 53

78k

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

$0.074 per 1M tokens at API prices$0.021 on Tencent Token Plan Standard

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. #21default of 24565.6%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #55default of 2501447

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #50default of 11639.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #27default of 11331.4%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #65default of 24321.6%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #39default of 15332.7%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #28default of 12350.0%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #112default of 12310.9%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #45default of 12612.9%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #41default of 24137.4%

Leader: Kimi K3.1 · 67.2%

All 41 benchmarks

show 31 more