GPT-6 Astra catches 33% more cross-file bugs than Opus 5 in code review
GPT-6 Astra in code review: Gains, privacy, and cost
CodeRabbit's early evaluation of OpenAI's GPT-6 Astra shows it catches about 4% more actionable bugs overall than GPT-5.6 Sol, and 22% more than Opus 5. The real edge appears in harder cross-file reviews, where Astra's gains jump to 20% over Sol and 33% over Opus 5. But stronger reasoning comes at a premium: Astra costs $10/$50 per million input/output tokens, 2.5x Sol's price. The team also used Astra to build NIGHTSHIFT, an action RPG with a 988-node skill tree, and discusses privacy options like zero data retention.
The biggest jump comes on harder cross-file reviews, where Astra's gains reach 20% over Sol and 33% over Opus 5.
- eyalitki
Comparison was done in the scope of coderabbit AI code review tool, which sadly makes it practically irrelevant.
My personal experience as a software engineer, and a former security researcher who did manual code audit, is that this code review tool has such poor results that it isn't worth the "noise" and friction it causes developers during C/I code review
- sdeframond
How do you guys review AI-generated code ?
In our team, frontend work is vibe-coded by the PO and merged as-is without review. Backend is coded by developers, using AI but in a slower, more controlled way.
Recently, our PO has been trying his hand at vibe-coding the backend. I must say he is a smart guy, almost technical but not quite a developer. We've just been handed a burst of stacked PRs amounting for ~15k LOC backend. We do not quite know what do to about it.
I know we are not the only ones in the situation. What's your experience and context ? What do you do ? What works for you what doesn't ?
- ramon156
Both OAI and Anthropic seem to have released a model that is slightly better but cost ~2x the previous iteration. Interesting play
- SneakyZero
Astra seems to be really slow. Maybe it intends to read more context. But from my experience it is definitely slower than 5.6 sol when handling same tasks.
- dude250711
Given that Fable is a Sol-class model, should Astra not be compared to Mythos in those tests?