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 2026-08-12

K-EXAONE 2.0

Measured on 39 benchmarks.

7.6

#65 of 72 models

Strengths

  • K-EXAONE 2.0
  • 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%0.8%#65 of 72
  2. Terminal-Bench v4-AA10%0.0%#62 of 72
  3. AutomationBench-AA5%3.9%#64 of 72
  4. AA-Briefcase v1.115%651#65 of 72
  5. GDP.pdf5%4.2%#63 of 72
  6. Terminal-Bench-Science-AA15%0.0%#53 of 72
  7. CritPt v2 Hard Subset10%4.0%#62 of 72
  8. AA-Omniscience v1.1 Accuracy10%14.5%#68 of 72
  9. HLE-Diamond10%5.7%#64 of 72
  10. AA-Omniscience v1.1 Non-hallucination5%69.6%#22 of 72

Bars show where K-EXAONE 2.0 sits among the 72 ranked models on each benchmark (right is best); the tick is the field median.

By category

  • K-EXAONE 2.0
  • Fable 5.2 (#1)
  • Field median
p25p50p75topField medianCodingAgents & computeruseProfessional workScience & researchReasoning &puzzlesKnowledge &accuracyLong documents
  1. Coding3 benchmarks12%#60 of 72
  2. Agents & computer use6 benchmarks11%#64 of 72
  3. Professional work5 benchmarks11%#65 of 72
  4. Science & research5 benchmarks15%#59 of 71
  5. Reasoning & puzzles3 benchmarks9%#63 of 69
  6. Knowledge & accuracy3 benchmarks17%#60 of 68
  7. Long documents2 benchmarks9%#63 of 69

Across 27 results on every current benchmark that measured K-EXAONE 2.0, not only this ranking’s. The percentage is its average standing among the 72 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 72 ranked models

Output tokens per task

#13 fewest of 60

55k

Not measured for K-EXAONE 2.0: cost per task, time per task, output speed, time to first token (no published API price yet).

This ranking’s benchmarks

10 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. #204default of 2593.9%

Leader: Gemini 4 Carbon · 77.8%

Professional work

AA-Briefcase v1.1

264 results
  1. #206default of 264651

Leader: Sonnet 5.5 · 1816

Science & research

CritPt v2 Hard Subset

133 results
  1. #115default of 1334.0%

Leader: Fable 5.2 · 76.5%

Coding

FrontierCode 2.0-AA

131 results
  1. #119default of 1310.8%

Leader: Fable 5.2 · 49.1%

Professional work

GDP.pdf

257 results
  1. #202default of 2574.2%

Leader: Gemini 4 Hydrogen · 32.8%

Knowledge & accuracy

HLE-Diamond

167 results
  1. #140default of 1675.7%

Leader: Fable 5.2 · 80.2%

Knowledge & accuracy

AA-Omniscience v1.1 Accuracy

140 results
  1. #133default of 14014.5%

Leader: Fable 5.2 · 79.1%

Knowledge & accuracy

AA-Omniscience v1.1 Non-hallucination

140 results
  1. #36default of 14069.6%

Leader: Gemini 4 Carbon · 95.8%

Science & research

Terminal-Bench-Science-AA

142 results
  1. #123default of 1420.0%

Leader: Fable 5.2 · 73.3%

Agents & computer use

Terminal-Bench v4-AA

255 results
  1. #190default of 2550.0%

Leader: Kimi K3.1 · 67.2%

All 39 benchmarks

show 29 more