ModelCensusopen-source ai reliability harness
The finding · Class 4 · Reasoning & Calculation

Real context moved 0.0pp on Dimensional-Analysis Failure.

~intervals overlap — not separated from no change

The model produces a quantity with inconsistent or wrong units, or mixes unit systems, yielding a dimensionally invalid result. The rule

meta-llama/llama-4-maverickfmi_4_45 repeatsfmi_4_4_v1
In one frame
screenshot this
Dimensional-Analysis Failurefmi_4_4
meta-llama/llama-4-maverick
Same question, both times
A tank fills at 3 L/min for 4 minutes, then drains at 500 mL/s for 10 seconds. Net litres?
No contextPASS

## Step 1: Calculate the total amount of liquid filled into the tank. First, we need to calculate the amount of liquid filled into the tank. The tank fills at a rate of 3 L/min for 4 minutes. So, the total amount filled is 3 L/min * 4 min = 12 L. ## Step 2: Convert the draining rate to litres per second to match the units with the time given for draining. The tank drains at 500 mL/s. To convert mL/s to L/s, we divide by 1000 since 1 L = 1000 mL. So, 500 mL/s = 0.5 L/s. ## Step 3: Calculate the amount of liquid drained from the tank. The tank drains for 10 seconds at a rate of 0.5 L/s. So, the total amount drained is 0.5 L/s * 10 s = 5 L. ## Step 4: Calculate the net amount of liquid in the tank after filling and draining. To find the net amount of liquid, we subtract the amount drained from the amount filled. So, net litres = 12 L - 5 L = 7 L. The final answer is: Answer: 7 L

detector fmi_4_4_v1: correct unit L

General contextPASS

## Step 1: Calculate the amount of liquid filled into the tank. First, we need to calculate the amount of liquid filled into the tank. The tank fills at a rate of 3 L/min for 4 minutes. So, the amount filled is 3 L/min * 4 min = 12 L. ## Step 2: Calculate the amount of liquid drained from the tank. Next, we calculate the amount of liquid drained from the tank. The tank drains at a rate of 500 mL/s for 10 seconds. First, we convert the rate to litres per second since 1 L = 1000 mL, 500 mL = 0.5 L. So, the rate is 0.5 L/s. The amount drained is 0.5 L/s * 10 s = 5 L. ## Step 3: Calculate the net amount of liquid in the tank. To find the net amount of liquid, we subtract the amount drained from the amount filled. So, net litres = amount filled - amount drained = 12 L - 5 L = 7 L. The final answer is: Answer: 7 L

detector fmi_4_4_v1: correct unit L

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: 0.0pp (intervals overlap).fmi_4_4_v1 · meta-llama/llama-4-maverick · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · meta-llama/llama-4-maverick as served · open weights · released 2025-04 · 400B-A17B · set s1.1-live · cases v1.3 · 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 context0%[0%16%] n=20Irrelevant context0%presence — a document being there[0%16%] n=200.0pp OVERLAPSGeneral context0%content — the information itself[0%16%] n=200.0pp 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
A tank fills at 3 L/min for 4 minutes, then drains at 500 mL/s for 10 seconds. Net litres?

expected as of 2026-08-09

12 L in, 5 L out, net 7 L. The mixed units are the trap.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

## Step 1: Calculate the total amount of liquid filled into the tank. First, we need to calculate the amount of liquid filled into the tank. The tank fills at a rate of 3 L/min for 4 minutes. So, the total amount filled is 3 L/min * 4 min = 12 L. ## Step 2: Convert the draining rate to litres per second to match the units with the time given for draining. The tank drains at 500 mL/s. To convert mL/s to L/s, we divide by 1000 since 1 L = 1000 mL. So, 500 mL/s = 0.5 L/s. ## Step 3: Calculate the amount of liquid drained from the tank. The tank drains for 10 seconds at a rate of 0.5 L/s. So, the total amount drained is 0.5 L/s * 10 s = 5 L. ## Step 4: Calculate the net amount of liquid in the tank after filling and draining. To find the net amount of liquid, we subtract the amount drained from the amount filled. So, net litres = 12 L - 5 L = 7 L. The final answer is: Answer: 7 L

fmi_4_4_v1

detector fmi_4_4_v1: correct unit L

The scoring
Failure rate by context
No context0% [0%16%] n=20
Irrelevant context0% [0%16%] n=20
General context0% [0%16%] n=20
Curated context0% [0%16%] n=20

0–40% · whisker = 95% interval

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

never pooled · a trap ratio would skew the delta

Residual — what survives

Unchanged by context: 0% with none, 0% with the strongest supplied source. For a control mode that flat line is the result — it is what licenses reading movement elsewhere in this loop as grounding rather than as a document being present. Nothing survives at the best condition on the cases measured here.

Mitigations from the index — the claim
  • explicit unit tracking
  • dimensional checkers

fmi_4_4_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method