arxiv
PublishedJuly 2, 2026 at 4:00 AM
▲bullish
WorkBench Revisited: Workplace Agents Two Years On
Publisher summary· verbatim
arXiv:2606.13715v2 Announce Type: replace Abstract: The best agent on WorkBench in March 2024, GPT-4, completed just 43% of tasks. We revisit the benchmark in June 2026 and find that the best agent to date, Claude Fable 5, now completes 98%. Beyond this considerable progress in frontier agent perfor
Models mentioned
01Related
05- arxiv6dA Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
- arxivMay 19EmoMind: Decoding Affective Captions from Human Brain fMRI
- arxivMay 11End-to-end PDDL Planning with Hardcoded and Dynamic Agents
- arxivApr 28ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection
- arxivApr 21SatBLIP: Context Understanding and Feature Identification from Satellite Imagery with Vision-Language Learning
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSPINE: Bridging the Cyber-Physical Gap with Agentic AI21marxivAI-Native Insurance for Agentic AI: Pricing, Underwriting, and End-to-End Automation21marxivCost-Optimal Foundation Model Deployment Portfolio for Transportation Management21marxivHarness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable21mThe Bubble Brief
WEEKLYRead benchmark insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗