← Back
software
SWE-bench
1 creator use or recommend it
1 use
1 critical
Last discussed Oct 10, 2026
A benchmark for measuring the performance of coding agents on software engineering tasks.
Recently discussed in
Working With Agents in Slack
Dan Shipper · Oct 10, 2026
Emergent: How Six Months of Tinkering Led To A $100M ARR Company
Mukund Jha · Jun 6, 2026
India’s Fastest Growing AI Startup
Mukund Jha · Mar 16, 2026
What creators say
MJ
Mukund Jha
uses
Used for: Used as a focus mechanism to attack hard problems and build world's best coding agent
Praised: Hardest benchmark at the time, provided clear progress feedback, led to found...
"I picked this benchmark SWE-bench which was the hardest benchmark at that time and told them while I figure out what we're going to build let's just attack this benchmark. It took us 3 months to crack that benchmark became world number one on that..."
More from Mukund Jha →+1 more mention from Mukund
"We looked at this benchmark called SWE-bench and we took on this challenge of becoming number one on that benchmark."
India’s Fastest Growing AI Startup
· Mar 16, 2026
Dan Shipper
critical
"It's like, oh, it's 1% better on SWE-bench, but like that doesn't necessarily mean anything for you."
Keep exploring
About this data
- ✓44,000+ mentions extracted from real podcast transcripts
- ✓Every quote links to the source episode
- ✓Sponsored mentions are always labeled
- ✓Critical takes are shown, never filtered out
Get an email when a new creator recommends it