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

Meta · released 2026-09-02

Muse Spark 1.3

Measured on 181 benchmarks across 2 reasoning efforts.

36.3

#15 of 61 models · best at max

Reasoning efforts in this ranking

max36.3#38 of 139
xhigh32.0#52 of 139

Strengths

  • Muse Spark 1.3
  • 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%23.1%#22 of 61
  2. Terminal-Bench v4-AA10%33.3%#20 of 61
  3. AA-Briefcase v1.115%1581#11 of 61
  4. AutomationBench-AA5%57.9%#26 of 61
  5. Terminal-Bench-Science-AA15%11.0%#20 of 61
  6. HLE-Diamond10%33.7%#15 of 61
  7. CritPt v2 Hard Subset10%46.0%#14 of 61
  8. AA-Omniscience v1.1 Accuracy10%38.0%#27 of 61
  9. AA-Omniscience v1.1 Non-hallucination5%74.8%#9 of 61
  10. GDP.pdf5%26.6%#9 of 61

Bars show where Muse Spark 1.3 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

#32 cheapest of 41

$1.2at max

Time per task

#14 quickest of 40

8.2 minat max

Output speed

#11 fastest of 52

190 tok/sat max

Time to first token

#35 quickest of 52

38sat max

Output tokens per task

#22 fewest of 44

91kat max

Token price

$0.198 per 1M tokens at API prices$0.099 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

241 results
  1. #54max of 24157.9%
  2. #59xhigh of 24156.8%

Leader: Gemini 4 Carbon · 77.8%

agentic

AA-Briefcase v1.1

247 results
  1. #20max of 2471581
  2. #44xhigh of 2471483

Leader: Sonnet 5.5 · 1814

reasoning

CritPt v2 Hard Subset

100 results
  1. #35max of 10046.0%

Leader: GPT-6 Astra · 71.5%

coding

FrontierCode 2.0-AA

97 results
  1. #43max of 9723.1%

Leader: Opus 5.5 · 46.4%

economics

GDP.pdf

240 results
  1. #29max of 24026.6%
  2. #45xhigh of 24024.2%

Leader: Muse Wonder Full · 32.6%

reasoning

HLE-Diamond

142 results
  1. #35max of 14233.7%
  2. #39xhigh of 14230.3%

Leader: Gemini 4 Carbon · 69.1%

knowledge

AA-Omniscience v1.1 Accuracy

111 results
  1. #63max of 11138.0%
  2. #65xhigh of 11137.8%

Leader: Fable 5.1 · 68.4%

knowledge

AA-Omniscience v1.1 Non-hallucination

111 results
  1. #12xhigh of 11177.5%
  2. #15max of 11174.8%

Leader: Gemini 4 Carbon · 95.8%

reasoning

Terminal-Bench-Science-AA

115 results
  1. #47max of 11511.0%
  2. #75xhigh of 1153.8%

Leader: Gemini 4 Carbon · 64.8%

coding

Terminal-Bench v4-AA

238 results
  1. #45max of 23833.3%
  2. #81xhigh of 23816.7%

Leader: Kimi K3.1 · 67.2%

All 181 benchmarks

show 171 more