跳过主要内容
评测来源/τ³-Banking
参与排名专业工作

τ³-Banking

Mercor · τ³-Banking 的公开模型评测结果。

官方评测
来源说明

该来源测量模型在「专业工作」领域的具体交付表现,原始成绩会和统一能力读数分开展示。

限制: 不同版本、推理设置和测试集可能导致分数变化,请结合数据时间阅读。

使用方式

参与排名的来源会影响能力分;参考、交叉参考和观察来源仅用于对比与核验。

本来源的模型成绩

Gemini 4 Argon58.173.22026-11-05
Claude Fable 5.255.769.82026-11-10
Gemini 4 Carbon55.769.82026-11-11
Claude Opus 5.55568.72026-11-05
Claude Fable 5.15467.32026-11-05
Claude Sonnet 5.55467.32026-11-05
Muse Spark 1.352.264.72026-11-05
Muse Wonder51.964.22026-11-05
Gemini 3.8 Flash48.859.72026-11-05
Qwen3.8 Max46.756.62026-11-05
GPT-6 Astra46.756.62026-11-05
Grok 4.645.755.22026-11-05
Claude Opus 54452.72026-11-05
GPT-5.6 Sol4351.22026-11-05
GPT-6 Sol4351.22026-11-05
Claude Haiku 5.54351.22026-11-05
GPT-6.1 Sol4351.22026-11-05
DeepSeek V4.1 Flash 101741.649.22026-11-05
GLM 5.340.547.62026-11-05
GPT-6 Luna40.247.22026-11-05
DeepSeek V4 Pro 081340.247.22026-11-05
GPT-5.6 Terra38.845.12026-11-05
DeepSeek V4.1 Flash37.843.72026-11-05
GLM-5.3 Flash37.843.72026-11-05
GLM-5.3 Flash37.843.72026-10-18
GLM-5.3 Flash37.843.72026-10-17
GPT-6.1 Terra37.142.62026-11-05
MiniMax M3.1 Flash36.141.22026-11-05
GPT-5.6 Luna35.740.62026-11-05
Kimi K334.739.12026-11-05
Grok 4.732.636.12026-11-05
MiniMax-M32119.22026-11-05
Gemini 3.5 Flash Lite18.615.72026-11-05
Inkling15.511.22026-11-05

常见问题