Provider-target drift

Model Drift Monitor

Every 6 hours, we collect official provider fingerprints and compare them against the baseline fingerprint to determine whether the model shows drift or capability degradation.

Monitoring status

Green is normal, yellow is watch, orange is suspected drift, red is confirmed drift, and grey is stale or missing data.

Claude Opus 5.5 / Anthropic—
GPT-6.1 Sol / OpenAI—

Claude Opus 5.5 / Anthropic

Anthropic · anthropic

Logical model
claude-opus-5-5
Status
Stale
Drift score
—

6 minutes ago

GPT-6.1 Sol / OpenAI

OpenAI · openai

Logical model
gpt-6.1-sol
Status
Stale
Drift score
—

4 hours ago

Cross-provider watch

OpenAI and Azure GPT targets, plus Anthropic and Bedrock Claude targets, are tracked separately so provider routing changes do not pollute official-model baselines.