minimax-m3
Ranked 12 of 14 overall. Strongest on monitoring at 92.6, weakest on credit analysis at 75.8.
Score
82.3
rank 12 of 14
Latency
55.9s
median per task
Cost
$0.014
per task at list prices
Capability profile
Mean score per category on question-answering, 0–100.
Score by category
Score and number of tasks per category, on question-answering.
Credit Analysis75.8 · 62
Monitoring92.6 · 20
Structured Products82.0 · 18
Research Intelligence90.2 · 10
Discovery & Prediction84.0 · 2
Where it sits
minimax-m3 against every other model on the board.
minimax-m3 beaten on both by haiku-5.5-highBest trade-off · no model beats these on bothBest-by-Task · hypothetical, not a model
On the research track
How it worked when it had to find its own evidence.
Delivered an answer
100%
of research tasks
Average steps
17.6
searches, reads and calculations per task
Where it lost the most
Its lowest-scoring tasks on question-answering.
FAIL
Spread Analysis
Credit Analysis
FAIL
MBS Prepayment
Structured Products
PARTIAL
New Issue Evaluation
Credit Analysis
PARTIAL
Total Return Projection
Credit Analysis
PARTIAL
Coverage Metrics
Financial Foundations