sonnet-5
Ranked 9 of 14 overall. Strongest on monitoring at 92.9, weakest on discovery & prediction at 80.2.
Score
85.2
rank 9 of 14
Latency
86.1s
median per task
Cost
$0.519
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 Analysis80.6 · 62
Monitoring92.9 · 20
Structured Products88.3 · 18
Research Intelligence88.2 · 10
Discovery & Prediction80.2 · 2
Where it sits
sonnet-5 against every other model on the board.
sonnet-5 beaten on both by kimi-k3 and 5 othersBest 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
16.3
searches, reads and calculations per task
Where it lost the most
Its lowest-scoring tasks on question-answering.
FAIL
MBS Prepayment
Structured Products
PARTIAL
Total Return Projection
Credit Analysis
PARTIAL
Relative Value
Credit Analysis
PARTIAL
New Issue Evaluation
Credit Analysis
PARTIAL
Relative Value
Credit Analysis