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 Minimax M3, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.
Lab
MiniMax
Proprietary
Coverage
78%
7 of 9 tracked signals
Best Arena rank
#9
WebDev Arena
Best suite
#16
Coding / 76
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 #16 in the coding view, with a 76 coding index. The strongest raw Arena signal is WebDev Arena at rank #9 with 1,680 public votes.
Best current lane
Coding
#16 / 76 coding index
Strongest raw signal
Code
#9, 1528 score
Commercial posture
$0.525
2.27s first token / 39 tok/s
Coverage gaps
Profile completeness
Arena categories
4/5
Code, Docs, Vision, Text
Commercial match
Live
MiniMax-M3
SWE-bench
Not listed
No confident software benchmark row
Raw identifier
minimax-m3
Performance cockpit
Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.
Vision Arena
Arena category
1228-1253 CI
Search Arena
Arena category
Not listed
No confident public Arena row for this category.
Coverage gap
Document Arena
Arena category
1420-1443 CI
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
$0.525
USD / 1M tokens
Input price
$0.300
USD / 1M input tokens
Output price
$1.20
USD / 1M output tokens
Latency
2.27s
Median time to first token
Output speed
39 tok/s
Median generation speed
Matched source row
MiniMax-M3Suite 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.
