Unverified50% confidenceFactExact time
DeepSeek V4 Pro在Humanity's Last Exam基准测试中得分37.7
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
DeepSeek V4 Pro深度评测：性能媲美GPT-5.5，成本仅1/12
bilibili63号炼金工坊6/18/2026
Related Claims
UnverifiedDeepSeek V4 Pro在CodeForces取得3206分，MMT-266评测达到95.2%通过率68% similarUnverifiedOmniMerge V4在HumanEval测试中得分84.76，与Q6K原版持平67% similarUnverifiedGLM-4.7在代码能力基准测试中超过DeepSeek V3.2及Claude Sonnet 4.565% similarUnverifiedDeepSeek V4 Pro相比Qwen3.6 27B Q4领先约6%，如果不是在推理数学项上意外翻车，领先幅度可能超过10%64% similarUnverifiedQwQ-32B在多项主流基准测试中与DeepSeek R1满血版表现几乎持平，部分任务上实现了反超64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/44835API
curl https://kongchang.com/api/v1/knowledge/claims/44835MCP
get_claim(id=44835)