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 2026-09-10

DeepSeek V4.1 Flash

Measured on 159 benchmarks across 2 reasoning efforts.

27.9

#32 of 68 models · best at max

Reasoning efforts in this ranking

max27.9#77 of 150
none15.6#121 of 150

Strengths

  • DeepSeek V4.1 Flash
  • 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%18.1% est.#33 of 68
  2. Terminal-Bench v4-AA10%26.8%#28 of 68
  3. AA-Briefcase v1.115%1417#33 of 68
  4. AutomationBench-AA5%68.9%#8 of 68
  5. Terminal-Bench-Science-AA15%9.0%#25 of 68
  6. HLE-Diamond10%19.1%#34 of 68
  7. CritPt v2 Hard Subset10%28.1% est.#37 of 68
  8. AA-Omniscience v1.1 Accuracy10%35.9% est.#33 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%37.0% est.#52 of 68
  10. GDP.pdf5%12.8%#40 of 68

Bars show where DeepSeek V4.1 Flash 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

Output speed

#8 fastest of 60

176 tok/sat max

Time to first token

#7 quickest of 60

1.2sat max

Token price

$0.019 per 1M tokens at API prices$0.0014 on Command Code GOAT

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.

Not measured for DeepSeek V4.1 Flash: cost per task, time per task, output tokens per task (no published API price yet).

This ranking’s benchmarks

6 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #9max of 24568.9%
  2. #102none of 24547.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #64max of 2501417
  2. #118none of 2501120

Leader: Sonnet 5.5 · 1813

economics

GDP.pdf

243 results
  1. #127max of 24312.8%
  2. #195none of 2433.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #70max of 15319.1%
  2. #124none of 1536.3%

Leader: Gemini 4 Carbon · 69.1%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #58max of 1269.0%
  2. #125none of 1260.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #62max of 24126.8%
  2. #119none of 2415.6%

Leader: Kimi K3.1 · 67.2%

All 159 benchmarks

show 153 more