·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Meta removes language that may have allowed it to scrape news sites1h◆Websites are closing their doors to AI agents3h◆Replit is no longer working with Anthropic, CEO says19h◆How Itaú is building generative AI for its entire customer base21h◆Roundtables: A Conversation With the Creator of AI-Designed Viruses22h◆India becomes the latest country to report rogue AI agent activity22h◆An Nvidia insider-turned-VC on why robotics hasn’t hit its ChatGPT moment, yet1d◆Physical AI is more than robots, says the Nvidia veteran now investing in it1d◆Elorian’s first AI model wants to reason with images, not just about them1d◆Jev is Vercel’s fastest-adopted AI model ever1d◆A week with RTX Spark: everything we’ve learned using Nvidia’s new laptops1d◆Mark Wahlberg on using AI in film ‘the right way’ and being open to an AI clone carrying on his legacy1d◆Meta’s new terms may allow it to train AI on news sites for free1d◆Veritas expands its anti-counterfeit chip to jewelry, trophies, and fragrance bottles1d◆Replit’s CEO says the future of work is the ‘self-driving company’1d◆Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets1d◆Judging the Judges: Confidence and Disagreement in Rubrics as Rewards1d◆Content associations with answer selection and engagement in supply chain community question answering1d◆ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents1d◆REKI: Registering Knowledge in VLAs1d◆Meta removes language that may have allowed it to scrape news sites1h◆Websites are closing their doors to AI agents3h◆Replit is no longer working with Anthropic, CEO says19h◆How Itaú is building generative AI for its entire customer base21h◆Roundtables: A Conversation With the Creator of AI-Designed Viruses22h◆India becomes the latest country to report rogue AI agent activity22h◆An Nvidia insider-turned-VC on why robotics hasn’t hit its ChatGPT moment, yet1d◆Physical AI is more than robots, says the Nvidia veteran now investing in it1d◆Elorian’s first AI model wants to reason with images, not just about them1d◆Jev is Vercel’s fastest-adopted AI model ever1d◆A week with RTX Spark: everything we’ve learned using Nvidia’s new laptops1d◆Mark Wahlberg on using AI in film ‘the right way’ and being open to an AI clone carrying on his legacy1d◆Meta’s new terms may allow it to train AI on news sites for free1d◆Veritas expands its anti-counterfeit chip to jewelry, trophies, and fragrance bottles1d◆Replit’s CEO says the future of work is the ‘self-driving company’1d◆Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets1d◆Judging the Judges: Confidence and Disagreement in Rubrics as Rewards1d◆Content associations with answer selection and engagement in supply chain community question answering1d◆ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents1d◆REKI: Registering Knowledge in VLAs1d◆
News/WorkBench Revisited: Workplace Agents Two Years On
arxiv
PublishedJuly 2, 2026 at 4:00 AM
▲bullish

WorkBench Revisited: Workplace Agents Two Years On

Source
arxiv.orgfull article ↗
Read on arxiv→
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
01
  • 01openai logo
    gpt-4
    openai/gpt-4
    0.0%IN $30.00/Mtok
Related
05
  • arxivJul 10
    A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
  • arxivMay 19
    EmoMind: Decoding Affective Captions from Human Brain fMRI
  • arxivMay 11
    End-to-end PDDL Planning with Hardcoded and Dynamic Agents
  • arxivApr 28
    ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection
  • arxivApr 21
    SatBLIP: Context Understanding and Feature Identification from Satellite Imagery with Vision-Language Learning
Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Mentioned models
02
  • 01
    gpt-4
    openai/gpt-4
  • 02
    Claude Fable 5
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#benchmark#safety#open-source#performance
Mentioned companies
01
OpenAI

No replies yet. Be first.

Mentioned models
02
  • 01
    gpt-4
    openai/gpt-4
  • 02
    Claude Fable 5
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#benchmark#safety#open-source#performance
Mentioned companies
01
OpenAI

Related coverage

More from ARXIV
arxivOptimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets1darxivJudging the Judges: Confidence and Disagreement in Rubrics as Rewards1darxivContent associations with answer selection and engagement in supply chain community question answering1darxivORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents1d
The Bubble Brief
MON · WED · FRI

Read benchmark insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews