UnifyBench

RankingGDPval-AA

GDPval-AA

Data updated 22 Oct 2026

Bucket
Agentic
Unit
elo
Direction
Higher is better
Version
v2
Display harness
Artificial Analysis GDPval-AA
Board
https://artificialanalysis.ai/evaluations/gdpval-aa

Compare published benchmark results with category weights →

Models

Results are ordered by score in the display harness, followed by models with no result. Other harnesses are listed separately below. Missing results remain unknown.

1–25 of 471 entries

ModelScoreEvidenceSource-recorded date
Claude Opus 5Anthropic1721official board2026-10-22
MiMo-V2.6-ProXiaomi1683official board2026-10-22
GLM-5.3-FlashZ.ai1642official board2026-10-22
Qwen3.8-Flash-NextQwen1628official board2026-10-22
Grok 4.6xAI1618official board2026-10-22
GPT-5.6 SolOpenAI1609official board2026-10-22
MiMo-V2.6-FlashXiaomi1607official board2026-10-22
Qwen 3.8-MaxQwen1604official board2026-10-22
Step 5 PreviewStepFun1587official board2026-10-22
Kimi K3Moonshot1533official board2026-10-22
DeepSeek V4-Pro 0813DeepSeek1449official board2026-10-22
Mistral Large 4Mistral1420official board2026-10-22
MiniMax-M3MiniMax1242official board2026-10-22
MiMo-V2.5-ProXiaomi1107official board2026-10-01
Solar Pro 4Upstage1106official board2026-10-22
Solar Mini 4Upstage1089official board2026-10-22
Agnes 2.5 Pro AlphaAgnes AI1088official board2026-09-19
Hy3Tencent1067official board2026-10-22
NVIDIA Nemotron 3 UltraNVIDIA1011official board2026-10-22
MiniMax-M2.7MiniMax1010official board2026-10-22
MiMo-V2.5Xiaomi997official board2026-10-22
Gemini 3.5 Flash-LiteGoogle983official board2026-10-22
Solar Open2 250BUpstage971official board2026-10-22
Step 3.7 FlashStepFun856official board2026-10-22
Gemini 3.1 ProGoogle792official board2026-10-22