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 M2.5, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.
Lab
MiniMax
Open weights
Coverage
56%
5 of 9 tracked signals
Best Arena rank
#45
WebDev Arena
Best suite
#16
Value / 72
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 value view, with a 72 value index. The strongest raw Arena signal is WebDev Arena at rank #45 with 7,842 public votes.
Best current lane
Value
#16 / 72 value index
Strongest raw signal
Code
#45, 1382 score
Commercial posture
$0.525
2.33s first token / 205 tok/s
Coverage gaps
Profile completeness
Arena categories
1/5
Code
Commercial match
Live
MiniMax-M2.5
SWE-bench
#3
bash-only
Raw identifier
minimax-m2.5
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
1374-1390 CI
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
bash-only
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
2.33s
Median time to first token
Output speed
205 tok/s
Median generation speed
Matched source row
MiniMax-M2.5Suite 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
Not listed
Not enough matched source rows for this composite view.
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.
