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 157 benchmarks across 2 reasoning efforts.

27.9

#29 of 61 models · best at max

Reasoning efforts in this ranking

max27.9#73 of 139
none15.4#113 of 139

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%18.4% est.#31 of 61
  2. Terminal-Bench v4-AA10%26.8%#26 of 61
  3. AA-Briefcase v1.115%1417#30 of 61
  4. AutomationBench-AA5%68.9%#8 of 61
  5. Terminal-Bench-Science-AA15%9.0%#23 of 61
  6. HLE-Diamond10%19.1%#31 of 61
  7. CritPt v2 Hard Subset10%27.9% est.#32 of 61
  8. AA-Omniscience v1.1 Accuracy10%35.9% est.#31 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%37.0% est.#45 of 61
  10. GDP.pdf5%12.8%#36 of 61

Bars show where DeepSeek V4.1 Flash 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

Output speed

#8 fastest of 52

213 tok/sat max

Time to first token

#7 quickest of 52

0.8sat max

Token price

$0.019 per 1M tokens at API prices$0.0012 on OpenCode Go

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

241 results
  1. #9max of 24168.9%
  2. #100none of 24147.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #61max of 2471417
  2. #115none of 2471119

Leader: Sonnet 5.5 · 1814

economics

GDP.pdf

240 results
  1. #124max of 24012.8%
  2. #191none of 2403.8%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #64max of 14219.1%
  2. #115none of 1426.3%

Leader: Gemini 4 Carbon · 69.1%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #56max of 1159.0%
  2. #113none of 1150.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #60max of 23826.8%
  2. #116none of 2385.6%

Leader: Kimi K3.1 · 67.2%

All 157 benchmarks

show 151 more