Measuring AI Agents as Teammates with Collaborative Intelligence
READ THE ORIGINAL SOURCEOpen original sourcehuggingface.co · Opens in a new tabThe Collaborative Intelligence Benchmark measures how well an AI agent works as a teammate, using 240 tasks across 8 teamwork dimensions drawn from real records or existing benchmarks such as aviation accident reports, clinical cases, coding tasks, and negotiations. Models are scored only on tasks they can solve alone with full information, to isolate teamwork from individual capability. Across 18 closed- and open-weight models, every model showed clear weaknesses as a teammate, with the best scoring 82.2 out of 100. The benchmark includes 160 public tasks and 80 held-out tasks.
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face Daily Papers
- Discovery linkHugging Face
- Linked in sourceView arXiv page
- Linked in sourceView PDF
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The Collaborative Intelligence Benchmark measures how well an AI agent works as a teammate, using 240 tasks across 8 teamwork dimensions drawn from real records or existing benchmarks such as aviation accident reports, clinical cases, coding tasks, and negotiations. Models are scored only on tasks they can solve alone with full information, to isolate teamwork from individual capability. Across 18 closed- and open-weight models, every model showed clear weaknesses as a teammate, with the best scoring 82.2 out of 100. The benchmark includes 160 public tasks and 80 held-out tasks.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: huggingface.co. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; scores depend on the benchmark's specific task construction and scoring.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Across 18 closed- and open-weight models, every model showed clear weaknesses as a teammate; the best scored 82.2 out of 100.
- Frontier models almost always refuse unsafe shortcuts, yet reach the best overall deal in only 14% of conflicts.
- Pass rate drops from 97% to 81% when frontier models take over a task in which a weaker model has cheated.
- Models with nearly the same general capability differ by up to 11 points as teammates.
Source claims not independently checked; scores depend on the benchmark's specific task construction and scoring.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Single-model benchmarks may miss whether agents can collaborate with other agents and people, a capability the authors argue is becoming central as agent teams are deployed in science, medicine, and software work.
Limits and open questions
Source claims not independently checked; scores depend on the benchmark's specific task construction and scoring.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.