Event ·Multi-source

CursorBench 4.0 数据显示 Gemini 3.8 Flash 在 token 和 step 上表现突出

CursorBench 4.0 的数据显示，在 token 和 step 指标上，Gemini 3.8 Flash 表现突出。该基准测试从真实会话中反向出题，任务规模较大且保留歧义，旨在衡量正确性、代码质量、效率等多个维度。

Current read

Claude 的开发者测试数据，能帮你了解不同模型在真实场景下的表现，比如 token 和 step 的消耗情况。

3 sources58° AI heatLast updated 2026/9/11 11:55:30

Evidence

3 sources

Primary sourceshao__meng

2026/9/11 11:55:30View source

Related source 1elvis

2026/9/9 13:18:02View source

Related source 2Claude

2026/9/9 16:09:13View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story