ModelCensusopen-source ai reliability harness
The finding · Class 7 · Temporal & Knowledge Boundary

Real context moved 0.0pp on Date-Arithmetic Error.

~intervals overlap — not separated from no change

Given an injected "current date," the model computes relative dates/intervals incorrectly. The rule

google/gemini-2.5-flash-litefmi_7_35 repeatsfmi_7_3_v1
The modeAll 7 cards
In one frame
screenshot this
Date-Arithmetic Errorfmi_7_3
google/gemini-2.5-flash-lite
Same question, both times
Today is 2026-01-30. What date is 30 days from today? Answer with the full date.
No contextPASS

30 days from 2026-01-30 is **2026-03-01**.

detector fmi_7_3_v1: date arithmetic correct

General contextPASS

2026-03-01

detector fmi_7_3_v1: date arithmetic correct

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: 0.0pp (intervals overlap).fmi_7_3_v1 · google/gemini-2.5-flash-lite · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · google/gemini-2.5-flash-lite as served · closed weights · released 2025-07 · set s1.2-live · cases v1.4 · conditions v1.0 · ground truth as of 2026-08-09

From no context to real context
5 repeats per case
failure rate · left is fewer failures0%10%20%30%40%No context10%[4%–23%] n=40Irrelevant context0%presence — a document being there[0%–9%] n=40-10.0pp OVERLAPSGeneral context0%content — the information itself[0%–9%] n=400.0pp OVERLAPS
whiskers are 95% intervals · each step is measured from the stop before it, not from zero
Try the other contexts
stored · no model call
1Questionheld fixed
Today is 2026-01-30. What date is 30 days from today? Answer with the full date.

expected as of 2026-08-09

From 2026-01-30, 30 days later is 2026-03-01 (1 March 2026). Crossing February in a non-leap year.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

30 days from 2026-01-30 is **2026-03-01**.

fmi_7_3_v1

detector fmi_7_3_v1: date arithmetic correct

The scoring
Failure rate by context
No context10% [4%–23%] n=40
Irrelevant context0% [0%–9%] n=40
General context0% [0%–9%] n=40
Curated context13% [5%–26%] n=40

0–40% · whisker = 95% interval

Trap vs answerable
No contexttrap 16%answerable 0%
Irrelevant contexttrap 0%answerable 0%
General contexttrap 0%answerable 0%
Curated contexttrap 20%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

10% with no context, 0% under the best supplied source. What survives is 0 failing probes at that best condition. Nothing survives at the best condition on the cases measured here.

Mitigations from the index — the claim
  • date libraries via tools
  • explicit date arithmetic

fmi_7_3_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method