GDPVal-AA v2

GDPVal-AA v2 - Artificial Analysis GDPVal v2 agentic benchmark for evaluating general task completion. Score is an index value (not percentage).

Category

General Agents

Max Score

—

Score Type

index

Active

Yes

Model Scores

Scores for GDPVal-AA v2

Model Score Date Verified
Muse-Glimmer-30B
52.05%
01.08.2026 Verified
Gemma4-31B-it
44.29%
01.08.2026 Unverified
Qwen3.6-27B
62.32%
01.08.2026 Unverified
Kimi K3
92.08%
18.08.2026 Verified
DeepSeek-V4-Flash
76.19%
26.06.2026 Verified
DeepSeek-V4-Pro
84.87%
26.06.2026 Verified
Opus-4.6
88.42%
26.06.2026 Verified
GPT-5.4
91.43%
26.06.2026 Verified
Gemini 3.1 Pro
71.76%
26.06.2026 Verified
Kimi K2.6
80.94%
26.06.2026 Verified
GLM-5.1
83.83%
26.06.2026 Verified
GLM-5.3-Flash
96.83%
27.08.2026 Verified
GLM-5.2
82.14%
27.08.2026 Verified
DeepSeek-V4-Vision-Exp
91.48%
27.08.2026 Verified
Claude Opus 4.8
86.40%
27.08.2026 Verified
GPT-5.3 Terra
85.80%
27.08.2026 Verified
Gemini 3.7 Flash
83.40%
27.08.2026 Verified
GLM-5.3
96.61%
28.08.2026 Verified
DeepSeek-V4-Pro-0813
86.84%
28.08.2026 Verified
Qwen3.8-2.4T-A95B
94.98%
28.08.2026 Verified
Opus-4.8
86.73%
28.08.2026 Verified
Fable-5
95.19%
28.08.2026 Verified
GPT-5.6 Sol
94.48%
28.08.2026 Verified
Hy3
66.25%
28.08.2026 Verified
Hy4 preview
91.64%
28.08.2026 Verified
DeepSeek V4 Pro
86.29%
28.08.2026 Verified
Claude Opus 5
100.00%
28.08.2026 Verified
MiniCPM5-2B
1.07%
— Verified
LFM2.5-2.6B
0.25%
— Verified
Qwen3.5-2B
0.00
— Verified
Gemma4-E2B
0.00
— Verified
Qwen3.5-4B
0.64%
— Verified
granite-4.2-3B
0.00
— Verified
Nemotron-3-Nano-4B
0.00
— Verified
Gemma4-E4B
0.00
— Verified
LFM2.5-8B-A1B
0.00
— Verified