跳过主要内容
评测来源/Finance Agent
参与排名专业工作

Finance Agent

Vals AI · Finance Agent 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 Argon65.473.22026-11-05
Gemini 3.8 Flash61.4467.92026-11-05
Muse Spark 1.260.666.82026-11-05
Muse Spark 1.359.9666.02026-11-05
Claude Fable 5.158.8864.52026-11-05
Claude Opus 558.6364.22026-11-05
Claude Opus 5.558.5964.12026-11-05
Claude Sonnet 5.558.163.52026-11-05
GLM-5.3 Flash57.8563.22026-11-05
GLM-5.3 Flash57.8563.22026-10-17
GLM-5.3 Flash57.8563.22026-10-18
MiMo V2.6 Pro57.3462.52026-11-05
Muse Spark 1.157.2162.32026-11-05
DeepSeek V4.1 Flash 101756.9662.02026-11-05
Claude Fable 556.3161.12026-11-05
Gemini 3.6 Flash56.361.12026-11-05
MiMo V2.6 Flash56.2861.12026-11-05
MiMo V2.6 Flash56.2861.12026-10-18
MiMo V2.6 Flash56.2861.12026-10-17
GLM 5.355.8460.52026-11-05
GPT-5.6 Luna55.0459.42026-11-05
Mistral Large 454.6858.92026-10-31
GPT-5.6 Terra54.4458.62026-11-05
Claude Haiku 5.554.1458.22026-11-05
Claude Opus 4.853.9257.92026-11-05
Claude Sonnet 553.9157.92026-11-05
GPT-5.6 Sol53.7657.72026-11-05
Grok 4.653.6857.62026-11-05
GPT-6 Astra53.5457.42026-11-05
DeepSeek V4.1 Flash53.4857.32026-11-05
Kimi K353.1156.82026-11-05
Grok 4.752.2555.72026-11-05
GPT-6.1 Sol52.0355.42026-11-05
GPT-5.551.7655.02026-11-05
Claude Opus 4.751.5154.72026-11-05
Claude Sonnet 4.651.0354.12026-11-05
Step 5 Preview50.6753.62026-11-05
Qwen3.8 Max50.5953.52026-11-05
DeepSeek V4 Pro 081350.3953.22026-11-05
GPT-6 Luna49.8752.52026-11-05
GLM-5.249.752.32026-11-05
DeepSeek V4 Flash 073149.5252.12026-11-05
GPT-6 Sol49.0551.42026-11-05
Grok 4.548.3550.52026-11-05
MiniMax-M348.2750.42026-11-05
Qwen3.7 Max47.7849.82026-11-05
Gemini 3.5 Flash Lite47.4449.32026-11-05
Inkling46.648.22026-11-05
GPT-5.4 mini45.3646.52026-11-05
Kimi K2.644.945.92026-11-05
GLM-5.144.7945.82026-11-05
MiMo-V2.5-Pro41.541.42026-11-05
Inkling Small41.2641.12026-11-05
Qwen3.6 Plus40.8540.52026-11-05
Qwen3.7 Plus38.2237.02026-11-05
Grok 4.337.7336.42026-11-05
MiMo-V2.536.7335.02026-11-05
Kimi K2.535.7933.82026-11-05
Mistral Medium 3.532.128.92026-10-11
Claude Haiku 4.531.0127.42026-11-05
Ling-3.0-flash (free)30.3126.52026-11-05
Gemini 3.1 Flash Lite Preview29.9926.12026-11-05
Grok 4.20 (Reasoning)28.4924.12026-11-05
MiniMax-M2.727.8923.32026-11-05
Laguna M.125.0319.52026-11-05
Laguna XS.215.66.92026-11-05
Command A9.040.02026-10-11
Command A Plus9.040.02026-11-05

常见问题