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 2026-10-17

DeepSeek V4.1 Flash 1017

Measured on 104 benchmarks across 3 reasoning efforts.

32.5

#19 of 61 models · best at max

Reasoning efforts in this ranking

max32.5#51 of 139
high28.5#70 of 139
none18.5#104 of 139

Strengths

  • DeepSeek V4.1 Flash 1017
  • 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%28.5%#14 of 61
  2. Terminal-Bench v4-AA10%33.8%#19 of 61
  3. AA-Briefcase v1.115%1570#14 of 61
  4. AutomationBench-AA5%66.6%#13 of 61
  5. Terminal-Bench-Science-AA15%12.9%#17 of 61
  6. HLE-Diamond10%25.3%#22 of 61
  7. CritPt v2 Hard Subset10%24.0%#38 of 61
  8. AA-Omniscience v1.1 Accuracy10%39.6%#24 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%35.9%#46 of 61
  10. GDP.pdf5%17.2%#28 of 61

Bars show where DeepSeek V4.1 Flash 1017 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

cheapest of 41

freeat max

Time per task

#16 quickest of 40

9.3 minat max

Output speed

#14 fastest of 52

174 tok/sat max

Time to first token

#12 quickest of 52

1.2sat max

Output tokens per task

#38 fewest of 44

139kat max

Token price

$0.019 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. #10high of 24168.5%
  2. #17max of 24166.6%
  3. #96none of 24148.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #24max of 2471570
  2. #58none of 2471426
  3. #62high of 2471416

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #62high of 10026.5%
  2. #67max of 10024.0%
  3. #96none of 1001.0%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #31max of 9728.5%
  2. #57high of 9716.8%
  3. #79none of 976.1%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #94max of 24017.2%
  2. #114high of 24014.2%
  3. #185none of 2404.4%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #47max of 14225.3%
  2. #60high of 14220.8%
  3. #109none of 1427.1%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #55max of 11139.6%
  2. #58high of 11138.9%
  3. #93none of 11121.9%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #16none of 11174.7%
  2. #70high of 11138.8%
  3. #75max of 11135.9%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #44max of 11512.9%
  2. #50high of 11510.5%
  3. #82none of 1152.4%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #44max of 23833.8%
  2. #57high of 23828.8%
  3. #105none of 2389.1%

Leader: Kimi K3.1 · 67.2%

All 104 benchmarks

show 94 more