Show HN: New eval from SWE-bench team evalutes LMs based on goals not ticketscodeclash.ai·5 pts·lieret·1
Show HN: Randomly switching between LMs at every step boosts SWE-bench scoreswebench.com·5 pts·lieret·1
Show HN: New SWE-bench leaderboard compares LMs without fancy agent scaffoldsswebench.com·2 pts·lieret·0