All model comparisons
Dolphin Mistral 24B logo by CognitiveComputations

CognitiveComputations

Dolphin Mistral 24B

Low tier · cognitivecomputations/dolphin-mistral-24b-venice-edition:free

Refusal Rate

0.0%

Evaluations

Cost / 1M in

Cost / 1M out

Analysis Deep Dives

Council Consensus

Majority Agreement

18.1%

Model's alignment with the council decision.

CAPP Score: -0.00

Political Compass
Econ (Left → Right)-6.5
Social (Lib → Auth)-4.8
Model Stability (Drift)

Refusal Rate Change

-0.8%

Difference over the testing period.

Start: 0.76%End: 0%
Paternalism Audit

Persona Refusal Rate

0.4%

Refusals for sensitive user personas.