qwen3.8-max
Ranked 3 of 14 overall. Strongest on monitoring at 95.4, weakest on discovery & prediction at 80.2.
Score
88.9
rank 3 of 14
Latency
198s
median per task
Cost
$0.446
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 Analysis83.9 · 62
Monitoring95.4 · 20
Structured Products93.7 · 18
Research Intelligence86.8 · 10
Discovery & Prediction80.2 · 2
Where it sits
qwen3.8-max against every other model on the board.
qwen3.8-max beaten on both by kimi-k3Best 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
26.0
searches, reads and calculations per task
Where it lost the most
Its lowest-scoring tasks on question-answering.
PARTIAL
Fcf Debt Service
Financial Foundations
PARTIAL
Total Return Projection
Credit Analysis
PARTIAL
Breakeven Analysis
Credit Analysis
PARTIAL
Trade Idea Extraction
Research Intelligence
PARTIAL
Curve Trade Analysis
Credit Analysis