Qwen3-235B has no normalized-retention advantage over Qwen3-30B from k=7 through k=5 on the four hardest generative datasets, but leads by 2.5 points at k=4 and 14.4 points at k=3.

Qwen3-235B has no normalized-retention advantage over Qwen3-30B from k=7 through k=5 on the four hardest generative datasets, but leads by 2.5 points at k=4 and 14.4 points at k=3. · CiteArk

Measurement results

0/4 assessed

0 supported0 disputed or conflicting4 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
printedValue: 2.5	2.5 percentage points	—	Not assessed
printedValue: 76.7	76.7%	—	Not assessed
printedValue: 62.3	62.3%	—	Not assessed
printedValue: 14.4	14.4 percentage points	—	Not assessed

Qwen3-235B has no normalized-retention advantage over Qwen3-30B from k=7 through k=5 on the four hardest generative datasets, but leads by 2.5 points at k=4 and 14.4 points at k=3.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results