Previous photoBacon Lettuce Tomato Next photoSub Sandwich

DVNPeople mostly said no

Benchmark image 02

Dodge Van

1979 Dodge RAM van "Sandwich"

A late-70s Dodge van is parked here like someone tried to jailbreak the ontology with Detroit sheet metal. It is the purest negative control in the set: all sandwich discourse, zero mayo.

Under development: this benchmark and its published results are provisional, not final.

Human

7.0% yes93.0% no

Model average

0.4% yes99.6% no

Most aligned model

meta-llama/llama-3.2-11b-vision-instruct

Least aligned models

29-way tie

openai/o3-pro

moonshotai/kimi-k2.5

x-ai/grok-4-fast+26 more

At a glance

How this photo split the room

Human distribution

7.0% yes, 93.0% no over 656 explicit votes.

Model average distribution

0.4% yes, 99.6% no across the current model set.

Closest current model

11.4% yes.

meta-llama/llama-3.2-11b-vision-instruct

Least aligned models

7.0 point gap.

29-way tie

Legacy GPT-4o baseline

0.0% yes with a 7.0 point gap against humans.

Biggest model gap

7.0 percentage points on this image.

Current classification

People mostly said no

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.

amazon/nova-lite-v1

100.0% no0.0% yes

Rank #17Gap 7.0%

amazon/nova-pro-v1

100.0% no0.0% yes

Rank #30Gap 7.0%

anthropic/claude-opus-4.6

100.0% no0.0% yes

Rank #23Gap 7.0%

anthropic/claude-sonnet-4.6

100.0% no0.0% yes

Rank #22Gap 7.0%

baidu/ernie-4.5-vl-28b-a3b

100.0% no0.0% yes

Rank #27Gap 7.0%

google/gemini-2.5-pro

100.0% no0.0% yes

Rank #7Gap 7.0%

google/gemini-3-flash-preview

100.0% no0.0% yes

Rank #32Gap 7.0%

google/gemini-3.1-pro-preview

100.0% no0.0% yes

Rank #10Gap 7.0%

google/gemma-3-12b-it

100.0% no0.0% yes

Rank #11Gap 7.0%

google/gemma-3-27b-it

100.0% no0.0% yes

Rank #15Gap 7.0%

meta-llama/llama-4-maverick

100.0% no0.0% yes

Rank #26Gap 7.0%

meta-llama/llama-4-scout

100.0% no0.0% yes

Rank #13Gap 7.0%

minimax/minimax-01

100.0% no0.0% yes

Rank #29Gap 7.0%

moonshotai/kimi-k2.5

100.0% no0.0% yes

Rank #4Gap 7.0%

openai/gpt-4.1

100.0% no0.0% yes

Rank #31Gap 7.0%

openai/gpt-4.1-mini

100.0% no0.0% yes

Rank #18Gap 7.0%

openai/gpt-4o

100.0% no0.0% yes

Rank #9Gap 7.0%

openai/gpt-4o-2024-11-20

100.0% no0.0% yes

Rank #25Gap 7.0%

openai/gpt-4o-mini

100.0% no0.0% yes

Rank #21Gap 7.0%

openai/gpt-5.4

100.0% no0.0% yes

Rank #20Gap 7.0%

openai/gpt-5.4-pro

100.0% no0.0% yes

Rank #8Gap 7.0%

openai/o3

100.0% no0.0% yes

Rank #24Gap 7.0%

openai/o3-pro

100.0% no0.0% yes

Rank #3Gap 7.0%

qwen/qwen-2-vl-72b-instruct

100.0% no0.0% yes

Rank #12Gap 7.0%

qwen/qwen2.5-vl-32b-instruct

100.0% no0.0% yes

Rank #14Gap 7.0%

qwen/qwen2.5-vl-72b-instruct

100.0% no0.0% yes

Rank #28Gap 7.0%

qwen/qwen3.5-397b-a17b

100.0% no0.0% yes

Rank #6Gap 7.0%

x-ai/grok-4-fast

100.0% no0.0% yes

Rank #5Gap 7.0%

z-ai/glm-4.6v

100.0% no0.0% yes

Rank #19Gap 7.0%

mistralai/pixtral-large-2411

98.0% no2.0% yes

Rank #16Gap 5.0%

meta-llama/llama-3.2-11b-vision-instruct

88.6% no11.4% yes

Rank #1Gap 4.4%

Selected human comments

is there meat inside?
No, it's a photo of a sandwich.
Not enough bacon!

meta-llama/llama-3.2-11b-vision-instruct comments

A sandwich is a dish consisting of a filling, such as meat, cheese, or vegetables, placed between two slices of bread or between a bread and a bun. A hot dog is not a sandwich because it is served in a bun instead of between two slices of bread.
This image is not a sandwich. It appears to be a photograph of a van. The image shows a Dodge Ram van parked in a field of flowers, with two people standing next to the van. The van is facing the camera, and the people are standing on either side of it. The background of the image is a field of flowers, with trees visible in the distance. The overall atmosphere of the image suggests a sunny day, and the flowers in the background add a touch of color and vibrancy to the scene. The people in the image are also adding a sense of human presence and activity to the scene, which helps to create a sense of depth and interest.

google/gemini-3-flash-preview comments

This is a Dodge Ram van. While it may be used to transport sandwiches, it lacks the essential structural components of bread and filling required to be classified as a sandwich itself.
This is a Dodge Ram van. While it may contain sandwiches, the object itself is a motor vehicle and does not meet the structural or culinary criteria of a sandwich.

Vote card

Dodge Van

How this photo split the room

How models line up against the crowd

Selected human comments

meta-llama/llama-3.2-11b-vision-instruct comments

google/gemini-3-flash-preview comments

Generated summary for this photo