AI source-led research benchmark
Produce a decision brief from a fixed source pack plus current public evidence.
Use the same source pack and questions to compare evidence traceability, unsupported claims, correction time and complete cost. Product roles suggest a shortlist, not a measured winner; check account access and data permissions before the pilot.
The evidence table.
Weights describe the proposed evaluation. Unknown or test-pending evidence receives no score and no total. Until every tool has complete evidence, row order is an editorial shortlist—not a performance ranking. Approved user runs remain separate.
Fixed protocol.
- 01Provide the same five-document source pack.
- 02Ask the same ten factual and three synthesis questions.
- 03Require a source for every consequential claim.
- 04Record unsupported claims, correction time and final analyst edits.
What counts as usable.
✓ Every key claim maps to a real source
✓ Sources support the attached claim
✓ Uncertainty is made visible
✓ The final brief needs limited factual correction
Open comparison library →Approved same-task runs
Structured observations make the protocol challengeable. Every submission is moderated; supplier claims and editorial results remain separate.
No approved community runs yet. No completed comparative result is claimed; use the protocol to collect your own evidence.
Test one tool under the published rules.
Report completion, elapsed time, retries, correction time and cost. Upload an output screenshot only when you own it or have permission.
The editorial table is a transparent decision model built from HubAI profile data. Community runs are shown only after moderation and never presented as a controlled HubAI laboratory result.
Editorial disclosure →