OpenAI's o3 outperforms GPT-4o on Convex evals by a small margin
Sujay Jayakar · Fullstack-Bench: The Eval for Coding Agents — with Sujay Jayakar, Chief Scientist, Convex · Mar 19, 2025 · at 17:56
Sujay Jayakar, Chief Scientist at Convex, discusses how frontier reasoning models perform on Convex's coding evaluations.
0:00 / 0:10exact quote · 10.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“You know, oh, three does do better than four. Oh, I mean, we use brain trust for tracking all this quantitatively, but I can't remember off the top of my head, but it's not like a slam dunk.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Sujay Jayakar
Cursor Composer solves Convex benchmarks but fails on alternative backends
“We did notice that I mean, with convex, it pretty much autonomously just solves the first two tasks. It has a few round trips on like some errors that are only show up and playing with the front end. And then it's able to complete this files task and kind of g…”
Claude 3.7 performed worse than Claude 3.5 on Convex evals
“For example, we just tried clod three seven and it performs worse than clod three five on convex evals with the same prompting.”
AI models struggle debugging Supabase RLS recursion compared to procedural code
“The particular example was like RLS rules and Supabase where debugging like an infinite loop for infinite recursion for the RLS rules was something that the models just really struggled with in a way that we didn't see for procedural code.”
AI hallucinates Convex code due to API similarities with Firebase
“I mean, I think one thing that's kind of interesting given these, you know, models inherent internal structure is that we noticed that a lot of hallucinations come from parts of our API that are like very close to Firebase, but not exactly Firebase.”
Claude 3.5 in Cursor autonomously codes for 10 plus minutes
“When it has the right feedback in cursor composer, and this was even on cloud three, five, it can just autonomously code for a 10 plus minutes and it can fix its own bugs. It can get to the point where it's like pretty much a fully working app with just an ini…”
End-to-end type safety and tight feedback loops improve AI agent performance
“It's like, you know, having just really tight feedback loops and having strong guardrails, like in convex, that's like end to end type safety, but that's like, you know, could take it in many, many different forms, right? Like making it so code is very cheap a…”