Expired50% confidenceBenchmarkExact time
Among open-source models, the best-performing MiniMax M3 and Kimi achieved a completion rate of only 4.6% on OSWorld 2.0.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
Valid until: 10/7/2026(expired)
Sources
OSWorld 2.0测评：最强AI Agent完成率仅20%，长流程是致命短板
bilibili熊二等兵7/1/2026
Related Claims
UnverifiedThe model used in the demonstration is MiniMax M3, not the highest-performing model on the market; the selection criteria were sufficiency and cost reliability.68% similarUnverifiedIn MiniMax's MMClaw evaluation, M2.7 approaches the level of Sonnet 4.6 in open-ended tool-calling scenarios67% similarUnverifiedDeepSeek V4 Pro's Terminal Bench score is slightly above open-source models Kimi K2.6, GLM 5.1, and Minimax M2.766% similarUnverifiedIn the complex codebase feature expansion task, when Composer 2.5 had already completed the task, MiniMax M3 was still analyzing the codebase, but the final output contained more comments and more comprehensive test coverage.63% similarUnverifiedMiniMax M2.7 received a composite score of 86.0 and was rated the best value for money.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/338176API
curl https://kongchang.com/api/v1/knowledge/claims/338176MCP
get_claim(id=338176)