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

Anthropic · released 2026-09-01

Fable 5.1

Measured on 240 benchmarks across 5 reasoning efforts.

49.5

#9 of 61 models · best at xhigh

Reasoning efforts in this ranking

xhigh49.5#19 of 139
max48.9#20 of 139
high46.9#22 of 139
medium42.8#30 of 139
low38.4#36 of 139

Strengths

  • Fable 5.1
  • 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%35.7%#8 of 61
  2. Terminal-Bench v4-AA10%55.1%#10 of 61
  3. AA-Briefcase v1.115%1651#7 of 61
  4. AutomationBench-AA5%57.8%#28 of 61
  5. Terminal-Bench-Science-AA15%40.5%#8 of 61
  6. HLE-Diamond10%58.8%#4 of 61
  7. CritPt v2 Hard Subset10%56.5%#7 of 61
  8. AA-Omniscience v1.1 Accuracy10%67.2%#1 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%30.5%#49 of 61
  10. GDP.pdf5%26.2%#10 of 61

Bars show where Fable 5.1 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

#33 cheapest of 41

$1.7at xhigh

Time per task

#28 quickest of 40

16 minat xhigh

Output speed

#41 fastest of 52

63 tok/sat xhigh

Time to first token

#39 quickest of 52

1.3 minat xhigh

Output tokens per task

#25 fewest of 44

97kat xhigh

Token price

$0.870 per 1M tokens at API prices$0.136 on Claude Max 20x

96.5% cache read · 0.08% fresh input · 2.85% cache write · 0.53% output

Measured from T3 Code usage in Claude Code, Oct 27 to Nov 2, high confidence. One app’s users, not everyone’s. $0.742 at the standard 97 / 2.5 / 0.5 mix.

This ranking’s benchmarks

10 of 10 measured

agentic

AutomationBench-AA

241 results
  1. #47max of 24159.4%
  2. #57xhigh of 24157.8%
  3. #67high of 24155.3%
  4. #71medium of 24154.7%
  5. #85low of 24152.2%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #8max of 2471670
  2. #11xhigh of 2471651
  3. #21high of 2471577
  4. #33medium of 2471525
  5. #46low of 2471479

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #14high of 10060.5%
  2. #21xhigh of 10056.5%
  3. #22medium of 10056.5%
  4. #30max of 10051.0%
  5. #34low of 10047.5%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #18xhigh of 9735.7%
  2. #25max of 9731.6%
  3. #26high of 9730.3%
  4. #29medium of 9728.8%
  5. #44low of 9722.8%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #20low of 24028.0%
  2. #25high of 24026.8%
  3. #26medium of 24026.8%
  4. #31xhigh of 24026.2%
  5. #32max of 24026.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #8max of 14260.1%
  2. #11xhigh of 14258.8%
  3. #19high of 14250.4%
  4. #25medium of 14245.0%
  5. #31low of 14237.4%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #1max of 11168.4%
  2. #2xhigh of 11167.2%
  3. #6high of 11164.7%
  4. #9medium of 11162.6%
  5. #18low of 11158.7%

Leader: this model · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #67low of 11140.2%
  2. #83xhigh of 11130.5%
  3. #84medium of 11130.2%
  4. #85max of 11130.0%
  5. #86high of 11129.8%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #18max of 11543.3%
  2. #21xhigh of 11540.5%
  3. #22high of 11539.5%
  4. #30medium of 11529.0%
  5. #37low of 11521.4%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #16xhigh of 23855.1%
  2. #20max of 23852.0%
  3. #21high of 23852.0%
  4. #30medium of 23844.9%
  5. #37low of 23840.4%

Leader: Kimi K3.1 · 67.2%

All 240 benchmarks

show 230 more