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

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Other · released 2026-07-09

JT-4.1 Flash 236B A21B 0709 (Reasoning)

Measured on 20 benchmarks.

19.0

#57 of 101 models

includes estimates: 35% of the mix is measured for this model

Strengths

  • JT-4.1 Flash 236B A21B 0709 (Reasoning)
  • Fable 5.2 (#1)
  • Field median
bestField medianFrontierCode 2.0-AATerminal-Benchv4-AAAutomationBench-AAAA-Briefcase v1.1GDP.pdfTerminal-Bench-Science-AACritPt v2 HardSubsetAA-Omnisciencev1.1 AccuracyHLE-DiamondAA-Omnisciencev1.1Non-hallucination
  1. FrontierCode 2.0-AA15%10.9% est.#58 of 101
  2. Terminal-Bench v4-AA10%3.0%#59 of 101
  3. AutomationBench-AA5%46.5%#51 of 101
  4. AA-Briefcase v1.115%1092#60 of 101
  5. GDP.pdf5%8.6%#70 of 101
  6. Terminal-Bench-Science-AA15%1.1% est.#57 of 101
  7. CritPt v2 Hard Subset10%27.9% est.#48 of 101
  8. AA-Omniscience v1.1 Accuracy10%33.8% est.#47 of 101
  9. HLE-Diamond10%14.4% est.#60 of 101
  10. AA-Omniscience v1.1 Non-hallucination5%41.8% est.#68 of 101

Bars show where JT-4.1 Flash 236B A21B 0709 (Reasoning) sits among the 101 ranked models on each benchmark (right is best); the tick is the field median.

By category

  • JT-4.1 Flash 236B A21B 0709 (Reasoning)
  • Fable 5.2 (#1)
  • Field median
p25p50p75topField medianCodingAgents & computeruseProfessional workLong documents
  1. Coding2 benchmarks45%#38 of 98
  2. Agents & computer use3 benchmarks43%#41 of 101
  3. Professional work4 benchmarks41%#50 of 101
  4. Long documents2 benchmarks34%#62 of 96

Across 11 results on every current benchmark that measured JT-4.1 Flash 236B A21B 0709 (Reasoning), not only this ranking’s. The percentage is its average standing among the 101 models in this ranking that took the same benchmarks: 100% beat them all, 0% trailed them all. A benchmark in two categories counts in both; a category needs two benchmarks.

Cost and speed

against 101 ranked models

Not measured for JT-4.1 Flash 236B A21B 0709 (Reasoning): cost per task, time per task, output speed, time to first token, output tokens per task (no published API price yet).

This ranking’s benchmarks

4 of 10 measured

Cost per task is what a subscriber pays: the model’s plan price, a share of API price. Models no plan sells are at API price.

Agents & computer use

AutomationBench-AA

259 results
  1. #119default of 25946.5%

Leader: Gemini 4 Carbon · 77.8%

Professional work

AA-Briefcase v1.1

264 results
  1. #137default of 2641092

Leader: Sonnet 5.5 · 1816

Professional work

GDP.pdf

257 results
  1. #171default of 2578.6%

Leader: Gemini 4 Hydrogen · 32.8%

Agents & computer use

Terminal-Bench v4-AA

255 results
  1. #140default of 2553.0%

Leader: Kimi K3.1 · 67.2%

All 20 benchmarks

show 16 more