Unverified60% confidenceBenchmarkExact time
Prime Agent, paired with the Opus 5 model, achieved a score of 95.5% on the ARC-AGI-3 benchmark, reportedly surpassing the human expert baseline reported in the paper.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
8/11/2026
First Seen
Valid until: 11/9/2026
Sources
Prime Agent：能自我改进底层框架的开源编程智能体
producthuntProductHunt Daily8/10/2026
Related Claims
UnverifiedOpus 5在ARC-AGI 3上的得分是次优模型的三倍70% similarUnverifiedGLM-5.3-Flash achieved a score of 57 on the Artificial Analysis composite intelligence index evaluation, on par with Claude Opus 4.8.68% similarUnverifiedClaude Opus在OSWorld 1.0上能达到83.5%的准确率64% similarUnverifiedGLM-5.3-Flash 在 Toolathlon Verified 得78.4分，OfficeQA Pro 得62.4分，均领先 Claude Opus 4.8。63% similarUnverifiedIn Automation Bench at medium reasoning intensity, GPT-6.1 Sol scored 35.4%, which is 2.2 percentage points higher than Opus 5.5 at one-third of the cost.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/732489API
curl https://kongchang.com/api/v1/knowledge/claims/732489MCP
get_claim(id=732489)