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

DeepSeek · released 2026-08-13

DeepSeek V4 Pro 0813

Measured on 103 benchmarks across 2 reasoning efforts.

23.0

#38 of 61 models · best at max

Reasoning efforts in this ranking

max23.0#91 of 139
none12.3#120 of 139

Strengths

  • DeepSeek V4 Pro 0813
  • 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%17.1%#33 of 61
  2. Terminal-Bench v4-AA10%14.1%#34 of 61
  3. AA-Briefcase v1.115%1254#39 of 61
  4. AutomationBench-AA5%56.7%#30 of 61
  5. Terminal-Bench-Science-AA15%5.7%#27 of 61
  6. HLE-Diamond10%19.5%#30 of 61
  7. CritPt v2 Hard Subset10%23.5%#40 of 61
  8. AA-Omniscience v1.1 Accuracy10%45.2%#15 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%5.9%#61 of 61
  10. GDP.pdf5%11.4%#40 of 61

Bars show where DeepSeek V4 Pro 0813 sits among the 61 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 61 ranked models

Cost per task

#34 cheapest of 41

$1.8at max

Time per task

#26 quickest of 40

15 minat max

Output speed

#37 fastest of 52

83 tok/sat max

Time to first token

#18 quickest of 52

1.8sat max

Output tokens per task

#26 fewest of 44

99kat max

Token price

$0.095 per 1M tokens at API prices

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

241 results
  1. #61max of 24156.7%
  2. #125none of 24134.9%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #94max of 2471254
  2. #151none of 247928

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #70max of 10023.5%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #55max of 9717.1%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #133max of 24011.4%
  2. #195none of 2403.6%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #63max of 14219.5%
  2. #107none of 1427.2%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #40max of 11145.2%
  2. #61none of 11138.6%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #109none of 1116.1%
  2. #110max of 1115.9%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #65max of 1155.7%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #88max of 23814.1%
  2. #142none of 2381.5%

Leader: Kimi K3.1 · 67.2%

All 103 benchmarks

show 93 more