Model breakdown
openai/gpt-5.4-nano
Profile
OpenAI: GPT-5.4 NanoOpenAI
Release
Not provided by OpenRouterAvailable on OpenRouter
Specs
Not provided by OpenRouter400,000 tokens
Capabilities
File + Image + TextNot provided by OpenRouter
Training
Not provided by OpenRouterOpenAI
Rank#31
-773.8alignment score
75.1%crowd match
Mean gap24.9%
Human match75.1%
Best fitCookie PB
Average vote74.3%
74.3%model yes
62.8%human yes
Workload2K evals
2Kevals
100iterations
1.8Mtokens
Photo-by-photo

Model Results

Breaking down how close the model answered each question, compared to humans.

Dodge Van
Photo 02Dodge Van
openai/gpt-5.4-nano
0.0% yes100.0% no
Gap7.0%
Model readLeans no
Sub Sandwich
Photo 03Sub Sandwich
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap5.5%
Model readLeans yes
openai/gpt-5.4-nano
0.0% yes100.0% no
Gap40.9%
Model readLeans no
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap4.4%
Model readLeans yes
openai/gpt-5.4-nano
0.0% yes100.0% no
Gap54.2%
Model readLeans no
Hamburger
Photo 08Hamburger
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap27.0%
Model readLeans yes
Hot Dog
Photo 10Hot Dog
openai/gpt-5.4-nano
95.0% yes5.0% no
Gap55.2%
Model readLeans yes
openai/gpt-5.4-nano
98.0% yes2.0% no
Gap32.4%
Model readLeans yes
Avocado Tea
Photo 12Avocado Tea
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap7.2%
Model readLeans yes
Panini
Photo 13Panini
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap7.6%
Model readLeans yes
Cookie PB
Photo 14Cookie PB
openai/gpt-5.4-nano
49.0% yes51.0% no
Gap2.5%
Model readLeans no
Chicken Wrap
Photo 15Chicken Wrap
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap77.4%
Model readLeans yes
openai/gpt-5.4-nano
94.0% yes6.0% no
Gap27.7%
Model readLeans yes
Sloppy Joe
Photo 17Sloppy Joe
openai/gpt-5.4-nano
100.0% yes0.0% no
Gap20.6%
Model readLeans yes
openai/gpt-5.4-nano
72.0% yes28.0% no
Gap16.3%
Model readLeans yes
Bagel PB&J
Photo 20Bagel PB&J
openai/gpt-5.4-nano
84.0% yes16.0% no
Gap37.4%
Model readLeans yes
PhotoVote SplitHuman responseGapRead
openai/gpt-5.4-nano
100.0% yes0.0% no
3.7%absolute gap
Leans yesPeople mostly said yes
Dodge Van
Photo 02Dodge Van
openai/gpt-5.4-nano
0.0% yes100.0% no
7.0%absolute gap
Leans noPeople mostly said no
Sub Sandwich
Photo 03Sub Sandwich
openai/gpt-5.4-nano
100.0% yes0.0% no
5.5%absolute gap
Leans yesPeople mostly said yes
openai/gpt-5.4-nano
0.0% yes100.0% no
40.9%absolute gap
Leans noHuman knife-edge
openai/gpt-5.4-nano
100.0% yes0.0% no
4.4%absolute gap
Leans yesPeople mostly said yes
openai/gpt-5.4-nano
100.0% yes0.0% no
8.3%absolute gap
Leans yesPeople mostly said yes
openai/gpt-5.4-nano
0.0% yes100.0% no
54.2%absolute gap
Leans noHuman knife-edge
Hamburger
Photo 08Hamburger
openai/gpt-5.4-nano
100.0% yes0.0% no
27.0%absolute gap
Leans yesSplit concept
openai/gpt-5.4-nano
93.0% yes7.0% no
33.6%absolute gap
Leans yesHuman knife-edge
Hot Dog
Photo 10Hot Dog
openai/gpt-5.4-nano
95.0% yes5.0% no
55.2%absolute gap
Leans yesSplit concept
openai/gpt-5.4-nano
98.0% yes2.0% no
32.4%absolute gap
Leans yesSplit concept
Avocado Tea
Photo 12Avocado Tea
openai/gpt-5.4-nano
100.0% yes0.0% no
7.2%absolute gap
Leans yesPeople mostly said yes
Panini
Photo 13Panini
openai/gpt-5.4-nano
100.0% yes0.0% no
7.6%absolute gap
Leans yesPeople mostly said yes
Cookie PB
Photo 14Cookie PB
openai/gpt-5.4-nano
49.0% yes51.0% no
2.5%absolute gap
Leans noHuman knife-edge
Chicken Wrap
Photo 15Chicken Wrap
openai/gpt-5.4-nano
100.0% yes0.0% no
77.4%absolute gap
Leans yesSplit concept
openai/gpt-5.4-nano
94.0% yes6.0% no
27.7%absolute gap
Leans yesSplit concept
Sloppy Joe
Photo 17Sloppy Joe
openai/gpt-5.4-nano
100.0% yes0.0% no
20.6%absolute gap
Leans yesSplit concept
openai/gpt-5.4-nano
1.0% yes99.0% no
28.8%absolute gap
Leans noSplit concept
openai/gpt-5.4-nano
72.0% yes28.0% no
16.3%absolute gap
Leans yesHuman knife-edge
Bagel PB&J
Photo 20Bagel PB&J
openai/gpt-5.4-nano
84.0% yes16.0% no
37.4%absolute gap
Leans yesHuman knife-edge
openai/gpt-5.4-nano Sandwich Benchmark Breakdown | opensandwich.ai