Unverified50% confidenceFactExact time

本次测试共产生147次模型调用

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/9/2026

First Seen

Valid until: 10/7/2026

Sources

国产平价AI模型网文写作能力实测：四款模型横向对比

bilibili灵蟹SoloEnt7/5/2026

Related Claims

Unverified万象模型提供了 1.3B 和 14B 参数量的不同规模版本62% similar Unverified千问3的235B参数MoE旗舰版在多项权威基准测试中接近甚至超越闭源顶级模型62% similar UnverifiedMixtral 8×22B 拥有 141B 总参数，但每次推理仅激活约 39B59% similar Unverified测试者评估Codex大概能完成看板上30%的任务59% similar Unverified评测者认为通义千问3.6 27B是30B级别中对高考数学题表现最好的模型58% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/329237

API

curl https://kongchang.com/api/v1/knowledge/claims/329237

MCP

get_claim(id=329237)