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 5.51813.3374.02026-11-05
Claude Opus 5.51799.8973.62026-11-05
Claude Fable 5.21785.3273.22026-11-10
Muse Wonder Full1729.3271.72026-10-18
Muse Wonder Full1729.3271.72026-11-05
Muse Wonder Full1729.3271.72026-10-17
Claude Fable 5.11669.4970.12026-11-05
Muse Wonder1658.6569.82026-10-18
Muse Wonder1658.6569.82026-11-05
Muse Wonder1658.6569.82026-10-17
Claude Opus 51654.6669.72026-11-05
Grok 4.71637.469.22026-11-05
Gemini 4 Carbon1610.6368.52026-11-11
Muse Spark 1.31581.3467.72026-11-05
Claude Haiku 5.51574.1267.52026-11-05
DeepSeek V4.1 Flash 10171570.4267.42026-11-05
GPT-6 Astra1568.5967.42026-11-05
GPT-6.1 Sol1555.0967.02026-11-05
Grok 4.61540.8566.62026-11-05
Claude Fable 51534.8166.52026-11-05
Ling-3.1-flash-1019152266.12026-11-05
MiMo V2.6 Pro1511.8865.92026-11-05
GLM 5.31502.8465.62026-11-05
Kimi K31497.2465.52026-11-05
MiMo V2.6 Flash1490.9165.32026-10-17
MiMo V2.6 Flash1490.9165.32026-10-18
MiMo V2.6 Flash1486.8365.22026-11-05
Gemini 4 Argon1485.0365.12026-11-05
GPT-5.6 Sol1478.6765.02026-11-05
GPT-6 Sol1476.4664.92026-11-05
MiniMax M3.1 Flash1475.9864.92026-11-05
GLM-5.3 Flash145364.32026-10-17
GLM-5.3 Flash1452.6364.32026-10-18
GLM-5.3 Flash1450.9464.22026-11-05
Step 5 Preview1425.1863.52026-11-05
DeepSeek V4.1 Flash1417.2263.32026-11-05
GPT-6.1 Terra1401.3662.92026-11-05
Ling-3.1-flash1400.0462.92026-10-17
Ling-3.1-flash1400.0462.92026-10-18
Ling-3.1-flash1396.9462.82026-11-05
Mistral Large 41390.862.62026-10-28
Qwen3.8 Max1382.3962.42026-11-05
Claude Sonnet 51356.2861.72026-11-05
Mistral Large 41348.3161.52026-11-05
GPT-5.6 Luna1338.9161.22026-11-05
GPT-6 Luna1337.0661.22026-11-05
GPT-5.6 Terra1333.1361.12026-11-05
Muse Spark 1.21323.6160.82026-11-05
Claude Opus 4.81319.6660.72026-11-05
Grok 4.51277.5459.62026-11-05
DeepSeek V4 Flash 07311255.3859.02026-11-05
DeepSeek V4 Pro 08131253.1658.92026-11-05
Claude Opus 4.71252.0658.92026-11-05
GLM-5.21226.2958.22026-11-05
Gemini 3.8 Flash1202.9957.62026-11-05
GPT-5.51135.3555.82026-11-05
MiniMax-M31089.0954.52026-11-05
GPT-5.5 Instant1086.1554.42026-10-09
Claude Sonnet 4.61061.853.82026-11-05
GLM-5.1964.7451.22026-11-05
Gemini 3.6 Flash955.6650.92026-11-05
Hy3947.2450.72026-11-05
Nex-N2-Pro940.2650.52026-11-05
DeepSeek V4 Pro921.950.02026-11-05
Qwen3.7 Max917.0749.92026-11-05
Qwen3.7 Plus915.3549.82026-11-05
Inkling Small912.6349.82026-11-05
MiMo-V2.5-Pro883.5949.02026-11-05
Nemotron 3 Ultra 550B A55B877.0948.82026-11-05
Kimi K2.7 Code858.0448.32026-11-05
Muse Spark 1.1850.7148.12026-11-05
Inkling833.0547.62026-11-05
Kimi K2.6820.0647.32026-11-05
Qwen3.6 27B816.0947.22026-11-05
Ling-3.0-flash (free)798.4246.72026-11-05
Grok 4.3762.5845.72026-11-05
MiMo-V2.5754.3445.52026-11-05
LongCat-2.0739.7345.12026-11-05
GPT-5.4 mini719.9144.62026-11-05
MiniMax-M2.7719.2744.62026-11-05
Claude Sonnet 4.5714.2244.42026-11-05
Qwen3.6 35B-A3B713.144.42026-11-05
Ring-2.6-1T657.9542.92026-11-05
Gemini 3.5 Flash Lite651.1742.82026-11-05
Claude Haiku 4.5616.541.82026-11-05
Qwen3.5 397B-A17B562.8940.42026-11-05
Mistral Medium 3.5523.2639.32026-11-05
Mistral Medium 3.5522.7839.32026-10-09
Qwen3.5 122B-A10B497.4938.62026-11-05
DeepSeek V3.1 Terminus458.5737.62026-11-05
Gemini 3.1 Pro Preview456.9937.52026-11-05
GPT-5 mini42936.82026-11-05
Qwen3 Coder Next404.436.12026-11-05
Command A Plus356.234.82026-11-05
Command A355.7834.82026-10-09
Qwen3.5 9B341.2834.42026-11-05
Gemini 2.5 Pro302.5133.42026-11-05
Mercury 2265.7932.42026-11-05
Trinity Large Thinking255.9232.12026-11-05
Mistral Small 4241.0431.72026-10-09
Mistral Large 3228.8431.42026-11-05
North Mini Code212.4531.02026-11-05
Gemini 3.1 Flash Lite207.9830.92026-11-05
o3 Mini High142.2529.12026-11-05
o3-mini141.6429.12026-10-09
Ministral 3 14B131.7528.82026-11-05
DeepSeek-R1128.9128.72026-11-05
Solar Pro 399.6727.92026-11-05
Nemotron 3 Nano 30B A3B77.9727.42026-11-05
Ministral 3 8B77.9727.42026-11-05
DeepSeek V3 032468.827.12026-11-05
Qwen3 32B025.32026-11-05
Nemotron 3 Super 120B A12B025.32026-11-05
gpt-oss-120b025.32026-11-05
gpt-oss-20b025.32026-11-05
Ministral 3 3B025.32026-11-05
Qwen3 8B025.32026-11-05
Qwen3 14B025.32026-11-05
Llama 4 Maverick025.32026-11-05
Llama 4 Scout025.32026-11-05

常见问题