Back to article
srikar
author

Srikar Kodati

Research Engineer, Benchmarks
,
Snorkel AI

Srikar Kodati is a Research Engineer at Snorkel AI, working on benchmarks and evaluations and for the Open Benchmark Grants program. Srikar previously developed Bank of America’s AML model and  large scale recommendation models at OTG Management.

The latest from Srikar Kodati

Inside Frontier-Bench: two Snorkel-built tasks that frontier agents still can’t crack
Blog
NEW
Inside Frontier-Bench: two Snorkel-built tasks that frontier agents still can’t crack

Frontier-Bench launched this week – the successor to Terminal-Bench, built to track what AI agents can and can’t do across real computer work. Terminal-Bench 2.1 has been saturating, with top agents clearing 75-84%; on Frontier-Bench’s launch set of 74 tasks across 7 domains, the best mode Opus 5 achieving 43.3%. Snorkel AI contributed as a task author and data partner,…

Jul 23, 2026 •
Derek Pham, Srikar Kodati
Learn more about Inside Frontier-Bench: two Snorkel-built tasks that frontier agents still can’t crack
Image

For models that need to be right. Not just good enough.

Request dataset samples
Talk to our team