Thoughts on AI, technology, and the future we're building.
New posts every week
Thoughts on AI, technology, and the future we're building.
New posts every week
A model-level benchmark profile for Llama 4 Maverick 17b 128e Instruct, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.
Lab
Meta
Proprietary
Coverage
11%
1 of 9 tracked signals
Best Arena rank
#80
Vision Arena
Best suite
#99
Reasoning / 28
Model profile
This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.
Analyst view
Its best composite result is rank #99 in the reasoning view, with a 28 reasoning proxy. The strongest raw Arena signal is Vision Arena at rank #80 with 7,063 public votes.
Best current lane
Reasoning
#99 / 28 reasoning proxy
Strongest raw signal
Vision
#80, 1147 score
Commercial posture
No price match
Artificial Analysis row not matched
Coverage gaps
Profile completeness
Arena categories
1/5
Vision
Commercial match
Missing
No Artificial Analysis match
SWE-bench
Not listed
No confident software benchmark row
Raw identifier
llama-4-maverick-17b-128e-instruct
Performance cockpit
Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.
Text Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
WebDev Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
Vision Arena
Arena category
1138-1157 CI
Search Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
Document Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
SWE-bench Verified
Software issue resolution
Not listed
No confident SWE-bench row matched to this model.
Coverage gap
Cost and speed
Price, latency, and throughput are only shown when a confident commercial source row is matched.
Blended price
Not listed
USD / 1M tokens
Input price
Not listed
USD / 1M input tokens
Output price
Not listed
USD / 1M output tokens
Latency
Not listed
Median time to first token
Output speed
Not listed
Median generation speed
Matched source row
Not listed
Suite position
These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.
Value
Quality, price, latency, and output speed
Not listed
Not enough matched source rows for this composite view.
Coding
Code Arena, SWE-bench, and output speed
Not listed
Not enough matched source rows for this composite view.
Agents
Search, documents, code, and latency
Not listed
Not enough matched source rows for this composite view.
Reasoning
Text, documents, vision, and mode signal
reasoning proxy
Long context
Document, search, and text benchmark proxy
Not listed
Not enough matched source rows for this composite view.
Lab context
Same-lab models make it easier to see whether this profile is a flagship, value play, specialist, or lower-coverage row.
