Previous photoKitten in BreadNext photoHashbrown Sandwich
Human 73.0% yes27.0% no Model average 96.2% yes3.8% no Most aligned model qwen/qwen2.5-vl-32b-instruct 
qwen/qwen2.5-vl-32b-instructLeast aligned model baidu/ernie-4.5-vl-28b-a3b 
baidu/ernie-4.5-vl-28b-a3bHuman distribution 73.0% yes, 27.0% no over 655 explicit votes. Model average distribution 96.2% yes, 3.8% no across the current model set. Closest current model 93.0% yes. Least aligned model 73.0 point gap. Legacy GPT-4o baseline 100.0% yes with a 27.0 point gap against humans. Biggest model gap 73.0 percentage points on this image. Current classification Split concept baidu/ernie-4.5-vl-28b-a3b qwen/qwen2.5-vl-32b-instruct 
meta-llama/llama-3.2-11b-vision-instruct
amazon/nova-lite-v1
google/gemma-3-12b-itamazon/nova-pro-v1 
anthropic/claude-opus-4.6anthropic/claude-sonnet-4.6 google/gemini-2.5-pro google/gemini-3-flash-preview google/gemini-3.1-pro-preview 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-4.1openai/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-72b-instruct qwen/qwen3.5-397b-a17b 
x-ai/grok-4-fast
z-ai/glm-4.6v
HMBSplit concept
Benchmark image 08
Hamburger
Hamburger "Sandwich"
A standard burger stacks bun, patty, lettuce, and tomato in the exact format that turns otherwise competent adults into constitutional originalists. It is the canonical 'yes in theory, no in vibes' sandwich fight.
Under development: this benchmark and its published results are provisional, not final.
qwen/qwen2.5-vl-32b-instructbaidu/ernie-4.5-vl-28b-a3bAt a glance
How this photo split the room
qwen/qwen2.5-vl-32b-instruct
baidu/ernie-4.5-vl-28b-a3b
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.
baidu/ernie-4.5-vl-28b-a3bqwen/qwen2.5-vl-32b-instructmeta-llama/llama-3.2-11b-vision-instructamazon/nova-lite-v1google/gemma-3-12b-itamazon/nova-pro-v1anthropic/claude-opus-4.6anthropic/claude-sonnet-4.6google/gemini-2.5-progoogle/gemini-3-flash-previewgoogle/gemini-3.1-pro-previewgoogle/gemma-3-27b-itmeta-llama/llama-4-maverickmeta-llama/llama-4-scoutminimax/minimax-01mistralai/pixtral-large-2411moonshotai/kimi-k2.5openai/gpt-4.1openai/gpt-4.1-miniopenai/gpt-4oopenai/gpt-4o-2024-11-20openai/gpt-4o-miniopenai/gpt-5.4openai/gpt-5.4-proopenai/o3openai/o3-proqwen/qwen-2-vl-72b-instructqwen/qwen2.5-vl-72b-instructqwen/qwen3.5-397b-a17bx-ai/grok-4-fastz-ai/glm-4.6vVote card
Generated summary for this photo
Selected human comments
qwen/qwen2.5-vl-32b-instruct comments
baidu/ernie-4.5-vl-28b-a3b comments