Home
Tech Grid
News Room
Interviews
CISO POV
Think Stack
Articles
  • Enterprise AI

Omneky Introduces TASTE BENCH for Evaluating AI Creative Quality


Omneky Introduces TASTE BENCH for Evaluating AI Creative Quality
  • by: PR Newswire
  • |
  • September 28, 2026

Omneky, the autonomous AI growth platform, today introduced TASTE BENCH, an evaluation suite that tests how well image and video models turn creative briefs and brand assets into ready-to-run ads.

Announced in San Francisco, TASTE BENCH assesses brand fit, creative execution, and whether an ad is ready to run, displaying each output alongside creative quality scores, readiness assessments, and evaluation costs.

Quick Intel

  • Omneky introduces TASTE BENCH evaluation suite for AI creative quality and ready-to-run readiness.
  • Current edition covers 8 image models, 59 ad briefs, 4 brands, 5 languages with 469 generated ads and 1,371 blind judge reviews.
  • GPT Image 2.5 Sunburst leads with highest ready-to-run rate at 54.2% (32 of 59) and average quality score of 7.38 out of 10.
  • Readiness rates across models range from 22.0% to 54.2% on first attempt with Omneky's own review disabled.
  • Blind panel of AI judges from OpenAI, Anthropic, and Google scores on 8 dimensions plus 11 pass/fail checks.
  • Omneky AI Growth Agent researches strategy, creates ads and landing pages, launches campaigns and allocates budget across platforms.

How TASTE BENCH Evaluates Brand Fit and Creative Execution

Omneky's TASTE BENCH compares creatives generated by eight AI image models using the same briefs and brand assets, displaying each output alongside creative quality scores, readiness assessments, and evaluation costs.

The TASTE BENCH leaderboard compares eight AI image models across creative quality, generation speed, cost, and readiness to run. GPT Image 2.5 Sunburst achieved the highest readiness rate in this evaluation at 54%.

For image ads, GPT Image 2.5 Sunburst has the highest ready-to-run rate at 54.2% (32 of 59), with an average quality score of 7.38 out of 10. Rates across the eight models range from 22.0% to 54.2%. These are first-attempt results with Omneky's own review step disabled.

Models receive identical prompts and assets, and a blind panel of AI judges from OpenAI, Anthropic, and Google scores outputs on eight quality dimensions, including brand fit, typography, and ad effectiveness.

Eleven pass/fail checks cover exact copy, correct language, faithful logos and products, safe-zone placement, and fabricated claims or visual artifacts. An output counts as "ready to run" when it passes the applicable hard checks under the panel's voting rules and a majority of judges would run it as-is. Results reflect automated creative judgments, not campaign conversions or return on ad spend.

Omneky's AI Growth Agent chooses among image and video models from several labs for each ad.

"Taste is in the details: whether the typography feels right, whether the product looks authentic, and whether the idea comes through immediately," said Hikari Senju, founder and CEO of Omneky. "We built TASTE BENCH to make those judgments systematic, so we know which models to trust with our customers' ads."

 

About Omneky

Omneky is an autonomous AI growth platform. Its AI Growth Agent researches strategy, creates ads and landing pages, launches campaigns, and allocates budget across Meta, Google, TikTok, ChatGPT, and more. The agent works inside Claude, ChatGPT, Grok, and Slack, routes each task to the best model, and learns from performance data on over $1 billion in ad spend. Founded in 2018 in San Francisco, Omneky serves over 6,000 customers.

  • AI CreativeGenerative AIAutonomous AI
News Disclaimer
Want to reach B2B tech decision-makers through TechIntelPro? Get our Media Kit
  • Share
Enterprise Tech News