ModelDial · Model results

deepseek-v4-pro

Compare tested reasoning efforts on private datasets. Scores and costs come from their recorded evaluations.

Highest overall score64.0

deepseek-v4-pro · max

Backend & testing
64
Frontend & interaction
63
Knowledge & reasoning
65

What changes with more effort

Compare scores, cost and time at neighboring tested efforts.

high max
Overall score
+2.9 pts
61.1 64.0
Reference cost
—
— $1.15
Evaluation time
+52.7%
61m 4s 93m 15s
View full comparison →

Results by reasoning effort

Select two or three configurations to compare scores and costs.

Swipe to see all results →

Model / effortOverallBackend & testingFrontend & interactionKnowledge & reasoningEvaluation timeReference costCompare
high61.156547561m 4s$0.98Partial cost
max64.064636593m 15s$1.15

How to read these results

The summary uses the same configuration as the highest overall score. A complete overall score requires all three axes; missing results appear as dashes.

Evaluation details · Published 9/30/2026