Unverified50% confidenceBenchmarkExact time

在中性模式下，Gemini 3.1 Pro Preview端到端准确率为40.8%

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/9/2026

First Seen

Valid until: 10/7/2026

Sources

腾讯DiscoBench：评测LLM搜索代理歧义澄清能力的首个基准

bilibili熊二等兵7/4/2026

Related Claims

Unverified在中性模式下，Doubao Seed 2.0 Pro端到端准确率最高，为43.1%，Gemini 3.1 Pro Preview为40.8%78% similar Partially VerifiedGemini 3.0 Pro的前端还原度被评为全场第一，但后端错误率较高76% similar UnverifiedGemini 3.5 Pro在Video ModeM多模态视频理解基准中得分82.1分，大幅领先其他模型76% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/396702

API

curl https://kongchang.com/api/v1/knowledge/claims/396702

MCP

get_claim(id=396702)