Skip to main content
Evaluation sources/GDPval-AA
ParticipatingProfessional work

GDPval-AA

Artificial Analysis · Public model evaluation results from GDPval-AA.

Official evaluation
Source description

This source measures concrete delivery performance in Professional work; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Opus 5.51866.2773.32026-11-05
Muse Wonder Full1857.0973.02026-10-18
Muse Wonder Full1857.0973.02026-11-05
Muse Wonder Full1857.0973.02026-10-17
Claude Sonnet 5.51837.8272.52026-11-05
Claude Fable 5.21831.3372.32026-11-10
Muse Wonder1770.3470.72026-10-18
Muse Wonder1770.3470.72026-10-17
Muse Wonder1770.3470.72026-11-05
Claude Fable 5.11763.2970.52026-11-05
DeepSeek V4.1 Flash 10171745.7770.02026-11-05
Gemini 4 Carbon1732.6869.62026-11-11
Claude Opus 51729.969.52026-11-05
Grok 4.71718.4269.22026-11-05
MiMo V2.6 Pro1689.468.42026-11-05
Muse Spark 1.31680.9968.22026-11-05
GLM 5.31656.8867.52026-11-05
Grok 4.61654.1567.52026-11-05
Ling-3.1-flash-10191652.9467.42026-11-05
GLM-5.3 Flash1649.3767.32026-11-05
GLM-5.3 Flash1642.1867.12026-10-18
GLM-5.3 Flash1642.1867.12026-10-17
Claude Haiku 5.51630.8366.82026-11-05
Gemini 4 Argon1630.6666.82026-11-05
Ling-3.1-flash1626.3866.72026-11-05
Claude Fable 51618.3966.52026-11-05
Ling-3.1-flash1617.9166.52026-10-17
Ling-3.1-flash1617.9166.52026-10-18
GPT-5.6 Sol1617.8366.52026-11-05
MiMo V2.6 Flash1613.5666.42026-11-05
Qwen3.8 Max1611.4566.32026-11-05
GPT-6.1 Sol1608.8966.22026-11-05
MiMo V2.6 Flash1607.5166.22026-10-18
MiMo V2.6 Flash1607.5166.22026-10-17
DeepSeek V4.1 Flash160066.02026-11-05
Step 5 Preview1593.9965.82026-11-05
GPT-6 Astra1583.6965.52026-11-05
Kimi K31542.7664.42026-11-05
GPT-6 Sol1515.8863.72026-11-05
Muse Spark 1.21480.0462.72026-11-05
GPT-6.1 Terra1475.6362.62026-11-05
Claude Sonnet 51470.3862.42026-11-05
GPT-5.6 Luna1468.2462.42026-11-05
MiniMax M3.1 Flash1465.3662.32026-11-05
Claude Opus 4.81461.7562.22026-11-05
GPT-5.6 Terra1461.4662.22026-11-05
DeepSeek V4 Pro 08131457.3762.12026-11-05
Gemini 3.8 Flash1445.4361.72026-11-05
GPT-6 Luna1444.4661.72026-11-05
DeepSeek V4 Flash 07311440.5761.62026-11-05
Mistral Large 41433.8561.42026-10-28
Grok 4.51389.3260.22026-11-05
GLM-5.21381.4960.02026-11-05
Claude Opus 4.71361.6959.42026-11-05
GPT-5.51359.2459.42026-11-05
Gemini 3.6 Flash1294.6357.62026-11-05
GPT-5.41255.6556.52026-11-05
MiniMax-M31249.9556.42026-11-05
Claude Sonnet 4.61240.556.12026-11-05
Muse Spark 1.11217.2555.52026-11-05
DeepSeek V4 Pro1166.2454.12026-11-05
Qwen3.7 Max1135.4653.22026-11-05
Inkling Small1132.5653.22026-11-05
MiMo-V2.5-Pro1128.6353.02026-11-05
GLM-5.11125.1552.92026-11-05
Nex-N2-Pro1109.4852.52026-11-05
Inkling1080.2251.72026-11-05
Hy31070.6451.52026-11-05
Kimi K2.61046.5350.82026-11-05
Kimi K2.7 Code1046.0150.82026-11-05
GPT-5.4 mini1021.7950.12026-11-05
GLM-4.71021.3950.12026-11-05
Nemotron 3 Ultra 550B A55B1020.6950.12026-11-05
MiniMax-M2.71016.1450.02026-11-05
MiMo-V2.51005.1549.72026-11-05
Qwen3.6 Plus996.8749.42026-11-05
Gemini 3.5 Flash Lite994.5249.42026-11-05
Qwen3.6 27B992.9849.32026-11-05
Ling-3.0-flash (free)956.9548.32026-11-05
Grok 4.3948.9148.12026-11-05
GPT-5925.4247.52026-11-05
Claude Sonnet 4.5915.4147.22026-11-05
Qwen3.6 35B-A3B899.4646.82026-11-05
LongCat-2.0876.6446.12026-11-05
Step 3.7 Flash863.7345.82026-11-05
Kimi K2.5846.6445.32026-11-05
Qwen3.5 122B-A10B821.5944.62026-11-05
Qwen3.5 397B-A17B800.6444.02026-11-05
Gemini 3.1 Pro Preview798.8844.02026-11-05
Qwen3.7 Plus774.843.32026-11-05
GPT-5 mini773.3643.32026-11-05
Mistral Medium 3.5768.8743.22026-11-05
GLM-4.6763.7643.02026-11-05
Mistral Medium 3.5760.3842.92026-10-09
Ring-2.6-1T752.942.72026-11-05
KAT-Coder-Pro V2742.0842.42026-11-05
Claude Haiku 4.5739.7642.42026-11-05
DeepSeek V3.1 Terminus717.6641.82026-11-05
DeepSeek V3.2699.0141.32026-11-05
MiMo-V2-Flash635.8139.52026-11-05
Qwen3.5 35B-A3B616.3339.02026-11-05
gpt-oss-120b615.6439.02026-11-05
Command A Plus521.8536.42026-11-05
Qwen3 Coder Next521.4136.42026-11-05
Command A514.1736.22026-10-09
GPT-5.5 Instant508.536.02026-10-09
Mercury 2501.7335.82026-11-05
Nemotron 3 Super 120B A12B497.4735.72026-11-05
Gemini 2.5 Pro463.0734.82026-11-05
Gemini 3.1 Flash Lite437.9234.12026-11-05
Gemma 4 12B Base434.7934.02026-11-05
Mistral Large 3427.6233.82026-11-05
Qwen3.5 9B426.5833.82026-11-05
Mistral Small 4362.132.02026-10-09
gpt-oss-20b347.1931.62026-11-05
Trinity Large Thinking343.7131.52026-11-05
Ling-2.6-flash326.0131.02026-11-05
North Mini Code318.6230.82026-11-05
DeepSeek-R1302.4730.42026-11-05
Nemotron Cascade 2 30B A3B272.2829.52026-11-05
Solar Pro 3272.0429.52026-11-05
Nemotron 3 Nano 30B A3B262.3229.32026-11-05
Ministral 3 14B254.8229.12026-11-05
o3 Mini High237.5328.62026-11-05
Nemotron 3 Nano Omni 30B A3B Reasoning236.9428.62026-11-05
o3-mini229.8228.42026-10-09
Ministral 3 8B221.0828.12026-11-05
DeepSeek V3 032476.7824.22026-11-05
Qwen3 32B40.8423.22026-11-05
Ministral 3 3B36.723.12026-11-05
GPT-4-12.8121.72026-11-05
Qwen3 14B-17.2521.62026-11-05
Qwen3 8B-41.1420.92026-11-05
Llama 4 Scout-155.7917.82026-11-05
Llama 4 Maverick-267.8114.72026-11-05

Frequently asked questions