Unverified80% confidenceFactTime unknown
Gemini 2.5 Pro在数学能力基准测试中与O3 Mini持平，两者都将其他模型远远甩在身后
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026
Sources
Gemini 2.5 Pro编程实测：Rust重构吊打Claude，前端却翻车
bilibili程序员韩老魔
Related Entities
Related Claims
UnverifiedGemini 3在SWE-bench基准测试中智能体场景下的得分远超同类模型81% similarVerifiedGemini 3.1 Pro新增了中档思考级别选项，而Gemini 3只有低和高两档77% similarUnverified在OmniDocBench V1.5测试中，OCR2在使用与Gemini 3 Pro相同数量的token的情况下取得了更高的性能表现76% similarUnverifiedClaude 4.5 与 Gemini 3 Pro 的对比结果并非一边倒，而是各有所长75% similarVerifiedGemini 3.5 Flash在几乎所有基准测试中超越了Gemini 3.1 Pro74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/20637API
curl https://kongchang.com/api/v1/knowledge/claims/20637MCP
get_claim(id=20637)