Unverified85% confidenceFactTime unknown
Gemini 3.5 Pro在MMLU Pro基准测试中得分89.4分，领先GPT 5.5和Claude
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Gemini 3.5 Pro深度评测：多模态断层领先，9.2分旗舰实力全解析
bilibiliEA同学
Related Entities
Related Claims
UnverifiedM2.7在SWE-bench Pro基准测试中得分56.22%，超过了Gemini 3.1 Pro79% similarVerifiedGemini 3.1 Pro在高级推理基准测试中达到77%，而Claude Opus 4.6为68%78% similarUnverified在综合性能排名中，Kimi K2.5得分64%，排名第五，前四名分别是Gemini 3 Pro（100%）、Claude Opus 4.5 Max（74%+）、GLM 4.7（65%）和GPT-5.2X（65%）76% similarUnverified在MMLU、HumanEval等主流基准测试上，Claude 3.5、GPT-4o、Gemini 1.5 Pro、Grok-2之间的分差已压缩至统计误差范围内76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13606API
curl https://kongchang.com/api/v1/knowledge/claims/13606MCP
get_claim(id=13606)