待验证50% 置信事实精确时间
Gemma 4 31B rivals much larger models like Gemini 5 and Kimi 2.5 on benchmark performance despite having far fewer parameters.
1
来源数
50%
置信度
中期 (~90 天)
时效性
2026/7/2
首次发现
有效期至：2026/9/30
来源
Gemma 4 Open-Source Model Local Deployment Guide: Ollama Installation & Mobile Setup
bilibili搞机零距离-2026/6/10
相关事实
待验证Gemma 4 31B 在评测中超越了智谱 GLM、DeepSeek V3.2 等同参数量级模型，并与 Gemini 5、Kimi 2.5 等大模型表现相当81% 相似待验证Gemma 4 31B outperforms models of similar parameter counts including Zhipu GLM and DeepSeek V3.2 on benchmark scores.69% 相似待验证Gemma 4 31B的前端HTML生成质量可与Gemini 3媲美66% 相似待验证Gemma 4 31B ranks in the top 27 on the overall capability leaderboard, ahead of models including Gemma 2.5 Pro.65% 相似已验证Gemma 4系列包含1B、2B、4B、26B（MOE）和31B（Dense）四款模型62% 相似
引用此条事实
Stable URI
https://kongchang.com/claim/47406API
curl https://kongchang.com/api/v1/knowledge/claims/47406MCP
get_claim(id=47406)