Ad creative analysis: benchmark methods and results
Models inspect five image ads and five video ads and explain their creative mechanisms. Ben blind-scores diagnostic accuracy, depth and explanation quality. Performance data is withheld, so the task measures creative diagnosis rather than causal attribution of sales.
Reviewed 16 October 2026 · Tests and editorial direction: Ben Nancarrow · AI-assisted writing and checks.
The fixed pack contains five static images and five videos. Models see the media, with original filenames and account performance withheld. They receive no spend, conversion, reach or brand-context evidence. Analysis and creative recommendations are generated as separate outputs.
What changes between prompts
Each asset is tested with a simple and a scaffolded prompt. The analysis scaffold covers attention, product relevance, proof, platform fit and other creative mechanisms. The action scaffold asks what to preserve, what to change and why. The media remains identical between conditions.
How the result is scored
The explanation is scored on diagnostic accuracy, depth of analysis and quality of explanation. Diagnostic accuracy is a critical dimension: a persuasive explanation with a weak diagnosis does not clear the task's readiness threshold. Recommendations for the next ad have their own score and page.
All 13 reviewed model results
Human-rated creative diagnosis / 10
Model
Result / setup
Scored outputs
Configuration / recorded test date
Cost / scored output
Claude Opus 5provisional
9.93/10Scaffolded prompt
21
thinking_max16 October 2026
$0.124Recorded spend
Google Gemini 4 Argonprovisional
9.93/10Scaffolded prompt
20
high16 October 2026
$0.035Recorded spend
Claude Fable 5.1provisional
9.90/10Scaffolded prompt
20
thinking_max16 October 2026
$0.415API-equivalent estimate
Claude Opus 5.5provisional
9.90/10Scaffolded prompt
20
thinking_max16 October 2026
$0.622API-equivalent estimate
Gemini 3.7 Flashprovisional
9.73/10Scaffolded prompt
60
reasoning_high16 October 2026
$0.005Recorded spend
Gemini 3.8 Flashprovisional
9.70/10Scaffolded prompt
20
reasoning_high16 October 2026
$0.010Recorded spend
Meta Muse Spark 1.3provisional
9.67/10Scaffolded prompt
20
high16 October 2026
$0.018Recorded spend
Meta Muse Wonderprovisional
9.43/10Scaffolded prompt
20
max16 October 2026
$0.081Recorded spend
Gemini 3.5 Flashprovisional
9.42/10Scaffolded prompt
60
default16 October 2026
$0.006Recorded spend
GPT-6 Astraprovisional
9.33/10Scaffolded prompt
20
xhigh16 October 2026
$0.154Recorded spend
Gemini 3.1 Pro Previewprovisional
9.32/10Scaffolded prompt
60
default16 October 2026
$0.008Recorded spend
Gemini 3.1 Flash-Liteprovisional
8.94/10Scaffolded prompt
60
default16 October 2026
$0.001Recorded spend
GPT-6 Solprovisional
8.00/10Scaffolded prompt
20
xhigh16 October 2026
$0.022Recorded spend
Recorded output counts can include repeats and both prompt conditions. Configurations and cost bases are retained; joint scores remain joint.
This record preserves the evidence and interpretation reviewed together. The live explorer can advance independently. Public results include provisional evidence; the methods above define what the scores measure.