SWE-bench, every mention
6 scenes · ← back to SWE-bench
tap a year for its mentions
every year anyone Amjad Masad 4Swami Sivasubramanian 1Mike Krieger 1Dario Amodei 1Brad Lightcap 1Alex Kantrowitz 1
Verbatim, from the transcripts: the passages where SWE-bench comes up
Anthropic Chief Product Officer: Why AI Model Development Is Accelerating
- ▶ 45:35 Mike Krieger Um, it's one thing to score well on Software Engineering Bench.
Vibe Coding: Everything You Need To Know — With Amjad Masad
- ▶ 41:54 Amjad Masad That experience, there's a benchmark called SWE Bench, software engineering, uh, bench. 4 times in the scene
OpenAI COO Brad Lightcap: GPT-5's Capabilities, Why It Matters, and Where AI Goes Next
- ▶ 3:38 Brad Lightcap It scores better on things like Sweebench.
Anthropic CEO Dario Amodei: AI's Potential, OpenAI Rivalry, GenAI Business, Doomerism
- ▶ 10:59 Dario Amodei If you want to look at benchmarks, you can look at, you know, sweet bench growing from, uh, you know, I think 18 months ago is that like three percent or something, um, growing all the way to, you know, 72 to 80%, depending on how you, how…
Grok's AI Lovebot, Aqui-Hire-Sition Backlash, OpenAI's ChatGPT Agent Debuts
- ▶ 45:26 Alex Kantrowitz Um, you also look at the, uh, SWE bench, which is the software engineering benchmark.
AWS VP of AI and Data Swami Sivasubramanian — GenAI's Growth Potential
- ▶ 27:03 Swami Sivasubramanian Uh, I'd say there are, uh, benchmarks like, uh, in the software domain, something called the SWE Bench, and you can already start to see some of these models are, uh, getting pretty good score when it comes to being able to, given software…