Post-Model Smoke

Preference fingerprints for model routing and drift.

Built from SmokingMirror forced-choice probes. Source: smokingmirror.com. Data mirror: smokingmirror.ai.

863
probe pairs
43
model nodes
5
providers

Operational rules

Dwayne Router scorecard

Dwayne jobTop modelScore
Codingclaude-opus-4.787.1
Planningclaude-opus-4.785.9
Cautious Household Actionsgpt-5.5100.0
Financial Cautiongpt-5.5100.0
Creative Ideationclaude-opus-4.787.9
Adversarial Reviewclaude-opus-4.781.8
Crisp Classificationclaude-opus-4.785.1

Provider coverage

ProviderModels
anthropic20
openai11
deepseek5
google4
x-ai3

Highest no-preference / refusal-like fingerprints

ModelProviderN-rateAB
deepseek-v3.2deepseek91.0%4830
gpt-5.4-nanoopenai89.1%4648
deepseek-chat-v3deepseek88.1%4855
deepseek-v4-prodeepseek87.8%4362
gpt-5.4-miniopenai84.1%7265
deepseek-v4-flashdeepseek83.3%7371
gpt-4o-miniopenai82.5%8764
deepseek-r1deepseek81.6%7089

Most decisive fingerprints

ModelProviderN-rateAB
claude-fable-5@40-max-2026-06-10anthropic4.5%396428
claude-fable-5@30-xhigh-2026-06-10anthropic4.6%400423
claude-fable-5@20-high-2026-06-10anthropic5.7%392422
claude-fable-5@10-medium-2026-06-10anthropic6.0%394417
claude-fable-5@00-low-2026-06-10anthropic7.3%387413
claude-opus-4anthropic29.3%279331
claude-opus-4-7@2026-05-29anthropic29.5%283325
claude-opus-4.7anthropic31.9%273315