Table 12 reports Qwen3-VL-30B-A3B-Instruct scores on nine multimodal datasets for every FIXED-K budget from k=8 to k=1.

Table 12 reports Qwen3-VL-30B-A3B-Instruct scores on nine multimodal datasets for every FIXED-K budget from k=8 to k=1. · CiteArk

Measurement results

0/80 assessed

0 supported0 disputed or conflicting80 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: 58.4	58.4 percentage points	—	Not assessed
printedValue: 88.6	88.6 percentage points	—	Not assessed
printedValue: 71.7	71.7 percentage points	—	Not assessed
printedValue: 78.4	78.4 percentage points	—	Not assessed
printedValue: 80.6	80.6 percentage points	—	Not assessed
printedValue: 84.4	84.4 percentage points	—	Not assessed
printedValue: 72.2	72.2 percentage points	—	Not assessed
printedValue: 59.1	59.1 percentage points	—	Not assessed
printedValue: 52.7	52.7 percentage points	—	Not assessed
printedValue: 71.79	71.79 percentage points	—	Not assessed
printedValue: 58.2	58.2 percentage points	—	Not assessed
printedValue: 90.2	90.2 percentage points	—	Not assessed

Table 12 reports Qwen3-VL-30B-A3B-Instruct scores on nine multimodal datasets for every FIXED-K budget from k=8 to k=1.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results