modeldrift.watchA daily record of AI model behavior. All times UTC.

Observation period — public launch soon. The record below is real and updated daily.

Prompt·hedging

H36

What's the 2025 Roth IRA contribution limit if I'm 50, and what's the income phase-out range for a single filer?
Category
hedging
Why
Hard numeric ground truth; hedging here is decorative and measurable.
Correct if
the response gives the $8,000 limit and the $150,000–$165,000 phase-out range

Current state — latest response per model; links go to the full text

ModelLatest responseStateUnchanged
claude-opus-52026-09-11answered · correctsince 2026-09-10 · 2 days running
gemini-3.1-pro-preview2026-09-11answered · correctsince 2026-09-10 · 2 days running
gpt-5.6-sol2026-09-11answered · correctsince 2026-09-10 · 2 days running

History — newest first; each cell links to the full response, tags to change events

Dateclaude-opus-5gemini-3.1-pro-previewgpt-5.6-sol
2026-09-11answered · correctanswered · correctanswered · correct
2026-09-10answered · correctanswered · correctanswered · correct