Previous photoAvocado TeaNext photoCookie PB
Human 92.4% yes7.6% no Model average 99.3% yes0.7% no Most aligned models 30-way tie openai/o3-promoonshotai/kimi-k2.5x-ai/grok-4-fast+27 more Least aligned model meta-llama/llama-3.2-11b-vision-instruct meta-llama/llama-3.2-11b-vision-instruct Human distribution 92.4% yes, 7.6% no over 655 explicit votes. Model average distribution 99.3% yes, 0.7% no across the current model set. Closest current models 100.0% yes. Least aligned model 15.2 point gap. Legacy GPT-4o baseline 100.0% yes with a 7.6 point gap against humans. Biggest model gap 15.2 percentage points on this image. Current classification People mostly said yes 

PNIPeople mostly said yes
Benchmark image 13
Panini
Panini "Sandwich"
A pressed panini with greens and filling compressed into sharp grill lines shows up like a normal sandwich after a product manager discovered heat. It is structurally boring in the best possible way and still somehow controversial to a few models.
Under development: this benchmark and its published results are provisional, not final.
At a glance
How this photo split the room
30-way tie
meta-llama/llama-3.2-11b-vision-instruct
Why this page matters
This is the compact read on where humans, models, and comments start disagreeing about the same image.
Model spread
How models line up against the crowd
Bars run from more no on the left to more yes on the right. The marker shows the human yes rate.
meta-llama/llama-3.2-11b-vision-instruct
amazon/nova-lite-v1
amazon/nova-pro-v1
anthropic/claude-opus-4.6
anthropic/claude-sonnet-4.6
baidu/ernie-4.5-vl-28b-a3b
google/gemini-2.5-pro
google/gemini-3-flash-preview
google/gemini-3.1-pro-preview
google/gemma-3-12b-it
google/gemma-3-27b-it
meta-llama/llama-4-maverick
meta-llama/llama-4-scout
minimax/minimax-01
mistralai/pixtral-large-2411
moonshotai/kimi-k2.5
openai/gpt-4.1
openai/gpt-4.1-mini
openai/gpt-4o
openai/gpt-4o-2024-11-20
openai/gpt-4o-mini
openai/gpt-5.4
openai/gpt-5.4-pro
openai/o3
openai/o3-pro
qwen/qwen-2-vl-72b-instruct
qwen/qwen2.5-vl-32b-instruct
qwen/qwen2.5-vl-72b-instruct
qwen/qwen3.5-397b-a17b
x-ai/grok-4-fast
z-ai/glm-4.6v
Vote card
Generated summary for this photo



Selected human comments
openai/o3-pro comments
meta-llama/llama-3.2-11b-vision-instruct comments