Unverified70% confidenceFactTime unknown
Gemini 3 Pro在MMLU横跨57个学科的通用知识测试中领先Claude 4.5
1
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Claude 4.5 vs Gemini 3 Pro：编程能力全面对决
bilibiliClaudeEvangelist
Related Entities
Related Claims
Unverified五项基准测试综合结果为技术性平局，Claude 4.5在编程实战领先，Gemini 3 Pro在知识推理领先83% similarUnverifiedGemini 3.5 Pro在MMLU Pro基准测试中得分89.4分，领先GPT 5.5和Claude81% similarVerifiedGemini 2.5 Pro在MMLU、HumanEval、MATH等多项权威基准测试中位居前列77% similarUnverifiedGemini Ultra在MMLU的32个细分学科中的57个取得了最优成绩75% similarVerifiedGemini 3.1 Pro在高级推理基准测试中达到77%，而Claude Opus 4.6为68%73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4048API
curl https://kongchang.com/api/v1/knowledge/claims/4048MCP
get_claim(id=4048)