Recursive Launches Flint AI Coding Model with Reported High SWE-Bench Score
Recursive has launched Flint, an AI coding model that the company claims was largely built by AI. Tech-Insider reports that Flint achieved an 89.7% score on the SWE-Bench benchmark, a detail not specified by other outlets. Wired highlights Recursive's focus on recursive self-improvement as its core strategy.
3 articles from 3 outlets covered this story. Their coverage differs on 3 points. The underlying claim is sourced from a benchmark.
What do all outlets agree on?
3 outlets covered “Recursive Launches Flint AI Coding Model with Reported High SWE-Bench Score”. All of them report the following:
- Recursive, a startup, launched a new AI model
- The model is named Flint
- Recursive claims the model was largely built by AI
Did outlets disagree about this?
Yes. Coverage of “Recursive Launches Flint AI Coding Model with Reported High SWE-Bench Score” differs on 3 points. Each account below is how a different outlet described the same event:
The model's development method is recursive self-improvement.
The model's performance is 'scary good'.
The SWE-Bench score is associated with the year 2026.
Which outlets covered this?
All 3 articles found on this story, grouped by the stance of the piece. Every link goes to the original publisher.