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 Claude Opus 4 20250514, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.
Lab
Anthropic
Proprietary
Coverage
67%
6 of 9 tracked signals
Best Arena rank
#60
Vision Arena
Best suite
#25
Agents / 95
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 #25 in the agents view, with a 95 agent proxy. The strongest raw Arena signal is Vision Arena at rank #60 with 2,226 public votes.
Best current lane
Agents
#25 / 95 agent proxy
Strongest raw signal
Vision
#60, 1188 score
Commercial posture
$32.81
8.75s first token / 37 tok/s
Coverage gaps
Profile completeness
Arena categories
2/5
Vision, Text
Commercial match
Live
Claude 4 Opus (Reasoning)
SWE-bench
#18
bash-only
Raw identifier
claude-opus-4-20250514
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
1408-1416 CI
WebDev Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
Vision Arena
Arena category
1175-1201 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
bash-only
Cost and speed
Price, latency, and throughput are only shown when a confident commercial source row is matched.
Blended price
$32.81
USD / 1M tokens
Input price
$18.75
USD / 1M input tokens
Output price
$75.00
USD / 1M output tokens
Latency
8.75s
Median time to first token
Output speed
37 tok/s
Median generation speed
Matched source row
Claude 4 Opus (Reasoning)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
value index
Coding
Code Arena, SWE-bench, and output speed
coding index
Agents
Search, documents, code, and latency
agent proxy
Reasoning
Text, documents, vision, and mode signal
reasoning proxy
Long context
Document, search, and text benchmark proxy
context proxy
Lab context
Same-lab models make it easier to see whether this profile is a flagship, value play, specialist, or lower-coverage row.
Claude Opus 4.6 Thinking
claude-opus-4-6-thinking
Best rank
#1
Coverage
67%
Claude Opus 4.7 Thinking
claude-opus-4-7-thinking
Best rank
#1
Coverage
33%
Claude Opus 4.7
claude-opus-4-7
Best rank
#2
Coverage
78%
Claude Opus 4.6 Search
claude-opus-4-6-search
Best rank
#2
Coverage
11%
Claude Opus 4.6
claude-opus-4-6
Best rank
#3
Coverage
78%
Claude Sonnet 4.6
claude-sonnet-4-6
Best rank
#7
Coverage
67%
Claude Opus 4.5 20251101 Thinking 32K
claude-opus-4-5-20251101-thinking-32k
Best rank
#12
Coverage
22%
Claude Sonnet 4.6 Search
claude-sonnet-4-6-search
Best rank
#12
Coverage
11%
