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 250 benchmarks across 5 reasoning efforts.

49.9

#9 of 67 models · best at xhigh

Reasoning efforts in this ranking

xhigh49.9#19 of 149
max49.1#20 of 149
high47.1#22 of 149
medium43.0#30 of 149
low38.6#38 of 149

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 67
  2. Terminal-Bench v4-AA10%55.1%#10 of 67
  3. AA-Briefcase v1.115%1649#7 of 67
  4. AutomationBench-AA5%57.8%#30 of 67
  5. Terminal-Bench-Science-AA15%40.5%#8 of 67
  6. HLE-Diamond10%58.8%#4 of 67
  7. CritPt v2 Hard Subset10%60.0%#7 of 67
  8. AA-Omniscience v1.1 Accuracy10%67.2%#1 of 67
  9. AA-Omniscience v1.1 Non-hallucination5%30.5%#55 of 67
  10. GDP.pdf5%26.2%#11 of 67

Bars show where Fable 5.1 sits among the 67 ranked models on each benchmark (right is best); the tick is the field median.

Cost and speed

against 67 ranked models

Cost per task

#41 cheapest of 50

$1.7at xhigh

Time per task

#32 quickest of 49

19 minat xhigh

Output speed

#37 fastest of 59

86 tok/sat xhigh

Time to first token

#46 quickest of 59

1.1 minat xhigh

Output tokens per task

#32 fewest of 53

97kat 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.

API default effort: high, per Artificial Analysis.

Token price

$0.854 per 1M tokens at API prices$0.133 on Claude Ultra

96.7% cache read · 0.06% fresh input · 2.75% cache write · 0.52% output

Measured from T3 Code usage in Claude Code, Oct 30 to Nov 5, 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

245 results
  1. #49max of 24559.4%
  2. #59xhigh of 24557.8%
  3. #69high of 24555.3%
  4. #73medium of 24554.7%
  5. #87low of 24552.2%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

250 results
  1. #8max of 2501669
  2. #11xhigh of 2501649
  3. #22high of 2501577
  4. #35medium of 2501525
  5. #48low of 2501478

Leader: Sonnet 5.5 · 1813

reasoning

CritPt v2 Hard Subset

116 results
  1. #18high of 11662.0%
  2. #21xhigh of 11660.0%
  3. #25medium of 11658.5%
  4. #31max of 11652.5%
  5. #39low of 11649.5%

Leader: GPT-6 Astra · 72.0%

coding

FrontierCode 2.0-AA

113 results
  1. #18xhigh of 11335.7%
  2. #26max of 11331.6%
  3. #29high of 11330.3%
  4. #32medium of 11328.8%
  5. #50low of 11322.8%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

243 results
  1. #21low of 24328.0%
  2. #26high of 24326.8%
  3. #27medium of 24326.8%
  4. #32xhigh of 24326.2%
  5. #33max of 24326.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

152 results
  1. #8max of 15260.1%
  2. #11xhigh of 15258.8%
  3. #19high of 15250.4%
  4. #25medium of 15245.0%
  5. #32low of 15237.4%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

122 results
  1. #1max of 12268.4%
  2. #2xhigh of 12267.2%
  3. #6high of 12264.7%
  4. #9medium of 12262.6%
  5. #19low of 12258.7%

Leader: this model · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

122 results
  1. #73low of 12240.2%
  2. #90xhigh of 12230.5%
  3. #91medium of 12230.2%
  4. #92max of 12230.0%
  5. #93high of 12229.8%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

126 results
  1. #18max of 12643.3%
  2. #21xhigh of 12640.5%
  3. #22high of 12639.5%
  4. #30medium of 12629.0%
  5. #38low of 12621.4%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

241 results
  1. #16xhigh of 24155.1%
  2. #20max of 24152.0%
  3. #21high of 24152.0%
  4. #30medium of 24144.9%
  5. #37low of 24140.4%

Leader: Kimi K3.1 · 67.2%

All 250 benchmarks

show 240 more