← All topics
ai-evaluation-metrics
Latest stories covering ai-evaluation-metrics, with summaries and links to related coverage.
1 stories · 1 reports · page 1 of 1
Connected topics
Why SWE-bench Verified no longer measures frontier coding capabilities
opinion
9 min read
SWE-bench Verified is becoming less reliable for measuring frontier coding capabilities due to contamination. SWE-bench Pro is recommended as a more accurate alternative for assessing models on autonomous software engineering tasks.