Thoughts on AI, technology, and the future we're building.
New posts every week
A model-level benchmark profile for Phi 4, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.
Lab
Microsoft
Open weights
Coverage
44%
4 of 9 tracked signals
Best Arena rank
#270
Text Arena
Best suite
#5
Agents / 100
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 #5 in the agents view, with a 100 agent proxy. The strongest raw Arena signal is Text Arena at rank #270 with 24,126 public votes.
Best current lane
Agents
#5 / 100 agent proxy
Strongest raw signal
Text
#270, 1256 score
Commercial posture
$0.219
0.49s first token / 41 tok/s
Coverage gaps
Profile completeness
Arena categories
1/5
Text
Commercial match
Live
Phi-4
SWE-bench
Not listed
No confident software benchmark row
Raw identifier
phi-4
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
1251-1261 CI
WebDev Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
Vision Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
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
$0.219
USD / 1M tokens
Input price
$0.125
USD / 1M input tokens
Output price
$0.500
USD / 1M output tokens
Latency
0.49s
Median time to first token
Output speed
41 tok/s
Median generation speed
Matched source row
Phi-4Suite 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.
Phi 3 Medium 4K Instruct
phi-3-medium-4k-instruct
Best rank
#298
Coverage
11%
Wizardlm 70b
wizardlm-70b
Best rank
#303
Coverage
11%
Phi 3 Small 8K Instruct
phi-3-small-8k-instruct
Best rank
#316
Coverage
11%
Wizardlm 13b
wizardlm-13b
Best rank
#328
Coverage
11%
Phi 3 Mini 4K Instruct June 2024
phi-3-mini-4k-instruct-june-2024
Best rank
#331
Coverage
11%
Phi 3 Mini 128K Instruct
phi-3-mini-128k-instruct
Best rank
#339
Coverage
11%
Phi 3 Mini 4K Instruct
phi-3-mini-4k-instruct
Best rank
#340
Coverage
11%