跳过主要内容
评测来源/GDPval-AA
参与排名专业工作

GDPval-AA

Artificial Analysis · GDPval-AA 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 Opus 5.51866.2773.92026-11-05
Muse Wonder Full1857.0973.62026-10-18
Muse Wonder Full1857.0973.62026-11-05
Muse Wonder Full1857.0973.62026-10-17
Claude Sonnet 5.51837.8273.12026-11-05
Muse Wonder1770.3471.22026-10-18
Muse Wonder1770.3471.22026-10-17
Muse Wonder1770.3471.22026-11-05
Claude Fable 5.11763.2971.02026-11-05
DeepSeek V4.1 Flash 10171745.7770.52026-11-05
Claude Opus 51729.970.12026-11-05
Grok 4.71718.4269.82026-11-05
MiMo V2.6 Pro1689.469.02026-11-05
Muse Spark 1.31680.9968.72026-11-05
GLM 5.31656.8868.12026-11-05
Grok 4.61654.1568.02026-11-05
Ling-3.1-flash-10191652.9467.92026-11-05
GLM-5.3 Flash1649.3767.82026-11-05
GLM-5.3 Flash1642.1867.62026-10-18
GLM-5.3 Flash1642.1867.62026-10-17
Claude Haiku 5.51630.8367.32026-11-05
Gemini 4 Argon1630.6667.32026-11-05
Ling-3.1-flash1626.3867.22026-11-05
Claude Fable 51618.3967.02026-11-05
Ling-3.1-flash1617.9167.02026-10-17
Ling-3.1-flash1617.9167.02026-10-18
GPT-5.6 Sol1617.8367.02026-11-05
MiMo V2.6 Flash1613.5666.92026-11-05
Qwen3.8 Max1611.4566.82026-11-05
GPT-6.1 Sol1608.8966.72026-11-05
MiMo V2.6 Flash1607.5166.72026-10-18
MiMo V2.6 Flash1607.5166.72026-10-17
DeepSeek V4.1 Flash160066.52026-11-05
Step 5 Preview1593.9966.32026-11-05
GPT-6 Astra1583.6966.02026-11-05
Kimi K31542.7664.92026-11-05
GPT-6 Sol1515.8864.22026-11-05
Muse Spark 1.21480.0463.22026-11-05
GPT-6.1 Terra1475.6363.02026-11-05
Claude Sonnet 51470.3862.92026-11-05
GPT-5.6 Luna1468.2462.82026-11-05
MiniMax M3.1 Flash1465.3662.82026-11-05
Claude Opus 4.81461.7562.72026-11-05
GPT-5.6 Terra1461.4662.62026-11-05
DeepSeek V4 Pro 08131457.3762.52026-11-05
Gemini 3.8 Flash1445.4362.22026-11-05
GPT-6 Luna1444.4662.22026-11-05
DeepSeek V4 Flash 07311440.5762.12026-11-05
Mistral Large 41433.8561.92026-10-28
Grok 4.51389.3260.62026-11-05
GLM-5.21381.4960.42026-11-05
Claude Opus 4.71361.6959.92026-11-05
GPT-5.51359.2459.82026-11-05
Gemini 3.6 Flash1294.6358.02026-11-05
GPT-5.41255.6556.92026-11-05
MiniMax-M31249.9556.82026-11-05
Claude Sonnet 4.61240.556.52026-11-05
Muse Spark 1.11217.2555.92026-11-05
DeepSeek V4 Pro1166.2454.52026-11-05
Qwen3.7 Max1135.4653.62026-11-05
Inkling Small1132.5653.52026-11-05
MiMo-V2.5-Pro1128.6353.42026-11-05
GLM-5.11125.1553.32026-11-05
Nex-N2-Pro1109.4852.92026-11-05
Inkling1080.2252.12026-11-05
Hy31070.6451.82026-11-05
Kimi K2.61046.5351.22026-11-05
Kimi K2.7 Code1046.0151.12026-11-05
GPT-5.4 mini1021.7950.52026-11-05
GLM-4.71021.3950.52026-11-05
Nemotron 3 Ultra 550B A55B1020.6950.42026-11-05
MiniMax-M2.71016.1450.32026-11-05
MiMo-V2.51005.1550.02026-11-05
Qwen3.6 Plus996.8749.82026-11-05
Gemini 3.5 Flash Lite994.5249.72026-11-05
Qwen3.6 27B992.9849.72026-11-05
Ling-3.0-flash (free)956.9548.72026-11-05
Grok 4.3948.9148.52026-11-05
GPT-5925.4247.82026-11-05
Claude Sonnet 4.5915.4147.52026-11-05
Qwen3.6 35B-A3B899.4647.12026-11-05
LongCat-2.0876.6446.52026-11-05
Step 3.7 Flash863.7346.12026-11-05
Kimi K2.5846.6445.62026-11-05
Qwen3.5 122B-A10B821.5944.92026-11-05
Qwen3.5 397B-A17B800.6444.42026-11-05
Gemini 3.1 Pro Preview798.8844.32026-11-05
Qwen3.7 Plus774.843.62026-11-05
GPT-5 mini773.3643.62026-11-05
Mistral Medium 3.5768.8743.52026-11-05
GLM-4.6763.7643.32026-11-05
Mistral Medium 3.5760.3843.22026-10-09
Ring-2.6-1T752.943.02026-11-05
KAT-Coder-Pro V2742.0842.72026-11-05
Claude Haiku 4.5739.7642.72026-11-05
DeepSeek V3.1 Terminus717.6642.12026-11-05
DeepSeek V3.2699.0141.52026-11-05
MiMo-V2-Flash635.8139.82026-11-05
Qwen3.5 35B-A3B616.3339.32026-11-05
gpt-oss-120b615.6439.22026-11-05
Command A Plus521.8536.62026-11-05
Qwen3 Coder Next521.4136.62026-11-05
Command A514.1736.42026-10-09
GPT-5.5 Instant508.536.32026-10-09
Mercury 2501.7336.12026-11-05
Nemotron 3 Super 120B A12B497.4736.02026-11-05
Gemini 2.5 Pro463.0735.02026-11-05
Gemini 3.1 Flash Lite437.9234.32026-11-05
Gemma 4 12B Base434.7934.22026-11-05
Mistral Large 3427.6234.02026-11-05
Qwen3.5 9B426.5834.02026-11-05
Mistral Small 4362.132.22026-10-09
gpt-oss-20b347.1931.82026-11-05
Trinity Large Thinking343.7131.72026-11-05
Ling-2.6-flash326.0131.22026-11-05
North Mini Code318.6231.02026-11-05
DeepSeek-R1302.4730.62026-11-05
Nemotron Cascade 2 30B A3B272.2829.72026-11-05
Solar Pro 3272.0429.72026-11-05
Nemotron 3 Nano 30B A3B262.3229.52026-11-05
Ministral 3 14B254.8229.22026-11-05
o3 Mini High237.5328.82026-11-05
Nemotron 3 Nano Omni 30B A3B Reasoning236.9428.82026-11-05
o3-mini229.8228.62026-10-09
Ministral 3 8B221.0828.32026-11-05
DeepSeek V3 032476.7824.32026-11-05
Qwen3 32B40.8423.32026-11-05
Ministral 3 3B36.723.22026-11-05
GPT-4-12.8121.82026-11-05
Qwen3 14B-17.2521.72026-11-05
Qwen3 8B-41.1421.12026-11-05
Llama 4 Scout-155.7917.92026-11-05
Llama 4 Maverick-267.8114.82026-11-05

常见问题