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

Alibaba · released 2026-08-14

Qwen 3.8 27B

Measured on 139 benchmarks across 4 reasoning efforts.

20.0

#44 of 68 models · best at xhigh

Reasoning efforts in this ranking

xhigh20.0#106 of 150
medium17.4#118 of 150
low15.6#122 of 150
none10.1#137 of 150

Strengths

  • Qwen 3.8 27B
  • 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%14.9%#40 of 68
  2. Terminal-Bench v4-AA10%5.6%#44 of 68
  3. AA-Briefcase v1.115%1391#35 of 68
  4. AutomationBench-AA5%48.2%#42 of 68
  5. Terminal-Bench-Science-AA15%0.5%#45 of 68
  6. HLE-Diamond10%15.3%#43 of 68
  7. CritPt v2 Hard Subset10%4.0%#58 of 68
  8. AA-Omniscience v1.1 Accuracy10%17.3%#62 of 68
  9. AA-Omniscience v1.1 Non-hallucination5%71.4%#19 of 68
  10. GDP.pdf5%16.4%#33 of 68

Bars show where Qwen 3.8 27B 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

#27 cheapest of 50

$0.26at xhigh

Time per task

#46 quickest of 49

41 minat xhigh

Output speed

#55 fastest of 60

45 tok/sat xhigh

Time to first token

#34 quickest of 60

5.5sat xhigh

Output tokens per task

#36 fewest of 53

110kat xhigh

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

$0.124 per 1M tokens at API prices$0.0091 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.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

245 results
  1. #100xhigh of 24548.2%
  2. #117medium of 24540.3%
  3. #134low of 24530.1%
  4. #170none of 24512.4%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #68xhigh of 2501391
  2. #70medium of 2501372
  3. #90low of 2501270
  4. #162none of 250901

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #86medium of 11616.5%
  2. #97low of 1165.5%
  3. #99xhigh of 1164.0%
  4. #104none of 1162.0%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #71xhigh of 11314.9%
  2. #76low of 11312.4%
  3. #79medium of 11311.5%
  4. #95none of 1133.7%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #105xhigh of 24316.4%
  2. #125medium of 24312.8%
  3. #148low of 24310.4%
  4. #182none of 2435.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

153 results
  1. #84xhigh of 15315.3%
  2. #121low of 1536.8%
  3. #122medium of 1536.7%
  4. #146none of 1534.2%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

123 results
  1. #110low of 12318.3%
  2. #112medium of 12317.9%
  3. #115xhigh of 12317.3%
  4. #123none of 1239.1%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

123 results
  1. #6none of 12382.0%
  2. #27xhigh of 12371.4%
  3. #63low of 12351.3%
  4. #85medium of 12334.6%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #91medium of 1261.0%
  2. #95xhigh of 1260.5%
  3. #98low of 1260.5%
  4. #107none of 1260.0%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #118xhigh of 2415.6%
  2. #120medium of 2415.1%
  3. #132low of 2412.5%
  4. #173none of 2410.0%

Leader: Kimi K3.1 · 67.2%

All 139 benchmarks

show 129 more