Expired50% confidenceFactExact time
DeepSeek V4 Pro's Terminal Bench score is slightly above open-source models Kimi K2.6, GLM 5.1, and Minimax M2.7
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
DeepSeek V4 Pro In-Depth Review: Performance Rivaling GPT-5.5 at 1/12 the Cost
bilibili63号炼金工坊6/18/2026
Related Claims
UnverifiedAmong open-source models, the best-performing MiniMax M3 and Kimi achieved a completion rate of only 4.6% on OSWorld 2.0.66% similarUnverifiedGLM-4.7 surpasses DeepSeek V3.2 and Claude Sonnet 4.5 in code capability benchmarks.65% similarUnverifiedGLM 5.2 beats nearly all commercial closed-source models on terminal benchmarks and SW Band Pro, ranking just behind Opus 4.8.63% similarUnverified在南宋临安追杀动作游戏测试中，DeepSeek V4 Pro的完成度超过Kimi K3，实现了可玩的MVP63% similarUnverifiedAlibaba released a preview of Qwen 3.6 MAX, which outperformed Claude 4.5 Opus and GLM 5.1 on coding tests including SWE Bench Pro and Terminal Bench; it is currently a closed-source model accessible only via Alibaba Cloud API or Qwen Studio.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/44336API
curl https://kongchang.com/api/v1/knowledge/claims/44336MCP
get_claim(id=44336)