I'm skeptical. Partially because if you go to https://www.swebench.com/, you can see this company underreported results from their competitors like Amazon Q Developer. I've also seen plenty of other projects claim they've reached 30%+ on SWE-bench without verifying or posting their results on this site.
> SWE-Bench has recently modified their submission requirements, now asking for the full working process of our AI model in addition to the final results -their condition to have us appear on the offical leaderboard. This change poses a significant challenge for us, as our proprietary methodology is evident in these internal processes. Publicly sharing this information would essentially open-source our approach, undermining the competitive advantage we’ve worked hard to develop. For now, we’ve decided to keep our model’s internal workings confidential. However we’ve made the model’s final outputs publicly available on GitHub for independent verification. These outputs clearly demonstrate our model’s 30% success rate on the SWE-Bench tasks.
