跳过主要内容
评测来源/AA-Briefcase
参与排名专业工作

AA-Briefcase

Artificial Analysis · AA-Briefcase 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

Claude Sonnet 5.51813.3374.62026-11-05
Claude Opus 5.51799.8974.22026-11-05
Muse Wonder Full1729.3272.32026-10-18
Muse Wonder Full1729.3272.32026-11-05
Muse Wonder Full1729.3272.32026-10-17
Claude Fable 5.11669.4970.72026-11-05
Muse Wonder1658.6570.42026-10-18
Muse Wonder1658.6570.42026-11-05
Muse Wonder1658.6570.42026-10-17
Claude Opus 51654.6670.32026-11-05
Grok 4.71637.469.82026-11-05
Muse Spark 1.31581.3468.32026-11-05
Claude Haiku 5.51574.1268.12026-11-05
DeepSeek V4.1 Flash 10171570.4268.02026-11-05
GPT-6 Astra1568.5968.02026-11-05
GPT-6.1 Sol1555.0967.62026-11-05
Grok 4.61540.8567.22026-11-05
Claude Fable 51534.8167.12026-11-05
Ling-3.1-flash-1019152266.72026-11-05
MiMo V2.6 Pro1511.8866.42026-11-05
GLM 5.31502.8466.22026-11-05
Kimi K31497.2466.02026-11-05
MiMo V2.6 Flash1490.9165.92026-10-17
MiMo V2.6 Flash1490.9165.92026-10-18
MiMo V2.6 Flash1486.8365.82026-11-05
Gemini 4 Argon1485.0365.72026-11-05
GPT-5.6 Sol1478.6765.52026-11-05
GPT-6 Sol1476.4665.52026-11-05
MiniMax M3.1 Flash1475.9865.52026-11-05
GLM-5.3 Flash145364.82026-10-17
GLM-5.3 Flash1452.6364.82026-10-18
GLM-5.3 Flash1450.9464.82026-11-05
Step 5 Preview1425.1864.12026-11-05
DeepSeek V4.1 Flash1417.2263.92026-11-05
GPT-6.1 Terra1401.3663.42026-11-05
Ling-3.1-flash1400.0463.42026-10-17
Ling-3.1-flash1400.0463.42026-10-18
Ling-3.1-flash1396.9463.32026-11-05
Mistral Large 41390.863.12026-10-28
Qwen3.8 Max1382.3962.92026-11-05
Claude Sonnet 51356.2862.22026-11-05
Mistral Large 41348.3162.02026-11-05
GPT-5.6 Luna1338.9161.72026-11-05
GPT-6 Luna1337.0661.72026-11-05
GPT-5.6 Terra1333.1361.62026-11-05
Muse Spark 1.21323.6161.32026-11-05
Claude Opus 4.81319.6661.22026-11-05
Grok 4.51277.5460.12026-11-05
DeepSeek V4 Flash 07311255.3859.52026-11-05
DeepSeek V4 Pro 08131253.1659.42026-11-05
Claude Opus 4.71252.0659.42026-11-05
GLM-5.21226.2958.72026-11-05
Gemini 3.8 Flash1202.9958.12026-11-05
GPT-5.51135.3556.22026-11-05
MiniMax-M31089.0955.02026-11-05
GPT-5.5 Instant1086.1554.92026-10-09
Claude Sonnet 4.61061.854.22026-11-05
GLM-5.1964.7451.62026-11-05
Gemini 3.6 Flash955.6651.32026-11-05
Hy3947.2451.12026-11-05
Nex-N2-Pro940.2650.92026-11-05
DeepSeek V4 Pro921.950.42026-11-05
Qwen3.7 Max917.0750.32026-11-05
Qwen3.7 Plus915.3550.32026-11-05
Inkling Small912.6350.22026-11-05
MiMo-V2.5-Pro883.5949.42026-11-05
Nemotron 3 Ultra 550B A55B877.0949.22026-11-05
Kimi K2.7 Code858.0448.72026-11-05
Muse Spark 1.1850.7148.52026-11-05
Inkling833.0548.02026-11-05
Kimi K2.6820.0647.72026-11-05
Qwen3.6 27B816.0947.62026-11-05
Ling-3.0-flash (free)798.4247.12026-11-05
Grok 4.3762.5846.12026-11-05
MiMo-V2.5754.3445.92026-11-05
LongCat-2.0739.7345.52026-11-05
GPT-5.4 mini719.9145.02026-11-05
MiniMax-M2.7719.2744.92026-11-05
Claude Sonnet 4.5714.2244.82026-11-05
Qwen3.6 35B-A3B713.144.82026-11-05
Ring-2.6-1T657.9543.32026-11-05
Gemini 3.5 Flash Lite651.1743.12026-11-05
Claude Haiku 4.5616.542.22026-11-05
Qwen3.5 397B-A17B562.8940.72026-11-05
Mistral Medium 3.5523.2639.62026-11-05
Mistral Medium 3.5522.7839.62026-10-09
Qwen3.5 122B-A10B497.4938.92026-11-05
DeepSeek V3.1 Terminus458.5737.92026-11-05
Gemini 3.1 Pro Preview456.9937.82026-11-05
GPT-5 mini42937.12026-11-05
Qwen3 Coder Next404.436.42026-11-05
Command A Plus356.235.12026-11-05
Command A355.7835.12026-10-09
Qwen3.5 9B341.2834.72026-11-05
Gemini 2.5 Pro302.5133.62026-11-05
Mercury 2265.7932.62026-11-05
Trinity Large Thinking255.9232.42026-11-05
Mistral Small 4241.0432.02026-10-09
Mistral Large 3228.8431.62026-11-05
North Mini Code212.4531.22026-11-05
Gemini 3.1 Flash Lite207.9831.12026-11-05
o3 Mini High142.2529.32026-11-05
o3-mini141.6429.32026-10-09
Ministral 3 14B131.7529.02026-11-05
DeepSeek-R1128.9128.92026-11-05
Solar Pro 399.6728.12026-11-05
Ministral 3 8B77.9727.62026-11-05
Nemotron 3 Nano 30B A3B77.9727.62026-11-05
DeepSeek V3 032468.827.32026-11-05
Qwen3 32B025.42026-11-05
Llama 4 Maverick025.42026-11-05
Llama 4 Scout025.42026-11-05
Qwen3 8B025.42026-11-05
Qwen3 14B025.42026-11-05
gpt-oss-120b025.42026-11-05
gpt-oss-20b025.42026-11-05
Ministral 3 3B025.42026-11-05
Nemotron 3 Super 120B A12B025.42026-11-05

常见问题