Article
ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM
ibm-research
• • 9Rohan Arora
rohan-arora
AI & ML interests
None yet
Recent Activity
upvoted a paper 15 days ago
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments updated a dataset about 1 month ago
ibm-research/ITBench-LiteOrganizations
published an article about 11 hours ago
upvoted a paper 15 days ago
updated a
dataset about 1 month ago
Task description defined twice in the input
3
#2 opened 2 months ago
by 
kyzor
Scenario indices discrepancy
2
#1 opened 2 months ago
by kyzor
Add CISO scenarios
2
#3 opened 3 months ago
by 
yana1205dev
test
#2 opened 3 months ago
by yana1205dev
published an article 3 months ago
Article
IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST
ibm-research
• • 19 finops new scenarios
2
#1 opened 4 months ago
by 
bturkkan
updated a
Space 4 months ago
updated a
dataset 4 months ago
activities
1
#1 opened 4 months ago
by 
bhavya24
test-pr
#1 opened 4 months ago
by rohan-arora
published a
dataset 4 months ago
published a
Space 4 months ago
published a
dataset 4 months ago