Unverified50% confidenceBenchmarkExact time
State-of-the-art models such as GLM-5.2, Claude-Sonnet-4.6, and GPT-5 achieve only approximately 50–54% Pass@8 on the hard subset.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedEarly GPT-3's HumanEval Pass@1 was below 10%, while top models such as GPT-4o and Claude 3.5 Sonnet have now consistently exceeded 85%.72% similarUnverifiedGLM-5.2 overtook GPT-5.5 on SweepBench Pro with a score of 62.1.70% similarUnverifiedAccording to hands-on evaluations, GLM-5.2's overall performance has reached the level of GPT-5.x and the Claude series flagship models.70% similarUnverifiedEarly GPT-4 achieved a resolution rate of less than 2% on SWE-bench, while recent top models have surpassed 50%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893310API
curl https://kongchang.com/api/v1/knowledge/claims/893310MCP
get_claim(id=893310)