[KongchangAI]
Unverified50% confidenceFactExact time

DeepSeek V4 Pro在MCP Atlas和Toolethlon Agent基准测试中得分超过GPT 5.4、Gemini 3.1 Pro和Kimi K2.6，仅次于GPT 5.5和Claude Opus 4.7

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

VerifiedGPT-5.5在多项能力上全面超越Claude 4.7和Gemini 3.1 Pro等模型78% similarVerifiedDeepSeek-V3和DeepSeek-R1在多项基准测试中达到了与GPT-4o相当的水平77% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/44836
API
curl https://kongchang.com/api/v1/knowledge/claims/44836
MCP
get_claim(id=44836)