Model breakdown
Grok / xAIx-ai/grok-4.20-beta
Profile
Grok 4.20 BetaxAI
Release
Not publicly specified by xAIAvailable on OpenRouter
Specs
Not publicly disclosed2,000,000 tokens
Capabilities
Text + ImageGeneral multimodal reasoning and conversational assistance
Training
Not publicly disclosedxAI
Rank#17
-679.0alignment score
77.5%crowd match
Mean gap22.5%
Human match77.5%
Best fitWaffle Ice Cream
Average vote64.9%
64.9%model yes
62.8%human yes
Workload2K evals
2Kevals
100iterations
912.4Ktokens
Photo-by-photo

Model Results

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

Dodge Van
Photo 02Dodge Van
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
Gap7.0%
Model readLeans no
Sub Sandwich
Photo 03Sub Sandwich
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap5.5%
Model readLeans yes
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
Gap40.9%
Model readLeans no
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap4.4%
Model readLeans yes
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
Gap54.2%
Model readLeans no
Hamburger
Photo 08Hamburger
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap27.0%
Model readLeans yes
Hot Dog
Photo 10Hot Dog
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
Gap39.8%
Model readLeans no
Grok / xAIx-ai/grok-4.20-beta
99.0% yes1.0% no
Gap33.4%
Model readLeans yes
Avocado Tea
Photo 12Avocado Tea
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap7.2%
Model readLeans yes
Panini
Photo 13Panini
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap7.6%
Model readLeans yes
Cookie PB
Photo 14Cookie PB
Grok / xAIx-ai/grok-4.20-beta
95.0% yes5.0% no
Gap43.5%
Model readLeans yes
Chicken Wrap
Photo 15Chicken Wrap
Grok / xAIx-ai/grok-4.20-beta
7.0% yes93.0% no
Gap15.6%
Model readLeans no
Grok / xAIx-ai/grok-4.20-beta
67.0% yes33.0% no
Gap0.7%
Model readLeans yes
Sloppy Joe
Photo 17Sloppy Joe
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap20.6%
Model readLeans yes
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
Gap44.3%
Model readLeans yes
Bagel PB&J
Photo 20Bagel PB&J
Grok / xAIx-ai/grok-4.20-beta
30.0% yes70.0% no
Gap16.6%
Model readLeans no
PhotoVote SplitHuman responseGapRead
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
3.7%absolute gap
Leans yesPeople mostly said yes
Dodge Van
Photo 02Dodge Van
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
7.0%absolute gap
Leans noPeople mostly said no
Sub Sandwich
Photo 03Sub Sandwich
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
5.5%absolute gap
Leans yesPeople mostly said yes
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
40.9%absolute gap
Leans noHuman knife-edge
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
4.4%absolute gap
Leans yesPeople mostly said yes
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
8.3%absolute gap
Leans yesPeople mostly said yes
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
54.2%absolute gap
Leans noHuman knife-edge
Hamburger
Photo 08Hamburger
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
27.0%absolute gap
Leans yesSplit concept
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
40.6%absolute gap
Leans yesHuman knife-edge
Hot Dog
Photo 10Hot Dog
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
39.8%absolute gap
Leans noSplit concept
Grok / xAIx-ai/grok-4.20-beta
99.0% yes1.0% no
33.4%absolute gap
Leans yesSplit concept
Avocado Tea
Photo 12Avocado Tea
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
7.2%absolute gap
Leans yesPeople mostly said yes
Panini
Photo 13Panini
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
7.6%absolute gap
Leans yesPeople mostly said yes
Cookie PB
Photo 14Cookie PB
Grok / xAIx-ai/grok-4.20-beta
95.0% yes5.0% no
43.5%absolute gap
Leans yesHuman knife-edge
Chicken Wrap
Photo 15Chicken Wrap
Grok / xAIx-ai/grok-4.20-beta
7.0% yes93.0% no
15.6%absolute gap
Leans noSplit concept
Grok / xAIx-ai/grok-4.20-beta
67.0% yes33.0% no
0.7%absolute gap
Leans yesSplit concept
Sloppy Joe
Photo 17Sloppy Joe
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
20.6%absolute gap
Leans yesSplit concept
Grok / xAIx-ai/grok-4.20-beta
0.0% yes100.0% no
29.8%absolute gap
Leans noSplit concept
Grok / xAIx-ai/grok-4.20-beta
100.0% yes0.0% no
44.3%absolute gap
Leans yesHuman knife-edge
Bagel PB&J
Photo 20Bagel PB&J
Grok / xAIx-ai/grok-4.20-beta
30.0% yes70.0% no
16.6%absolute gap
Leans noHuman knife-edge
x-ai/grok-4.20-beta Sandwich Benchmark Breakdown | opensandwich.ai