WBench / Navigation / Evidence

VWA-World

Source-listed configuration · X-Era AI

Current report

Reported scores

Average: 81.70points / 100
Quality: 82.10points / 100
Setting: 83.80points / 100
Interaction: 85.90points / 100
Consistency: 87.70points / 100
Physical: 68.90points / 100

Read the original leaderboard

Provenance

Result origin: Published by WBench; not run by Rather
Evaluation source: Mixed evaluation
Source publication date: Oct 12, 2026
Imported: Oct 13, 8:38 AM UTC
Protocol: Navigation · 158 cases
Checkpoint: Not pinned by source

Generated by: Not established by this leaderboard row
Scored by: self-evaluation-plus-organizer-vlm

Submission report

The 16 submitted local metrics were checked for aggregate schema and case counts; per-case local scores were not supplied. Organizer evaluated Scene Adherence, Subject Adherence, and Causal Fidelity.

16 self-evaluated + 3 organizer-evaluated metrics

Source revision & integrity

Upstream revision: 004aa621b4e526f733b3e5cc8305ee241f04048f
Snapshot SHA-256: 14f13b9229d883ed8c5a7b5d9d20759333e5838e226204b0f7a19d422604ac20
Original label: X-Era AI | VWA-World |

Loading benchmark results…

VWA-World

Reported scores

Provenance