GDPval-AA normalized

An Artificial Analysis normalized score for economically valuable tasks.

  • In index
  • Agentic
ModelsModels with a result.107
Top resultBest result on this test.67.3%Claude Opus 5.5
Top-3 spreadPoints from first to third.6.9 pts
YearYear of release.N/A

Result and price

020406080100$0.1$0.3$1$3$10$30$100RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

107 results
#ModelResultThe score from the source.
04Grok 4.759.8%
08GLM-5.357.3%
10Grok 4.655.3%
17Kimi K351.2%
18GPT-6 Sol49.3%
28Grok 4.543.5%
29GPT-6 Luna43.4%
30GLM-5.242.9%
33GPT-5.541.8%
35GPT-5.436.6%
36MiniMax M336.5%
46GLM-5.130.2%
47Grok 4.329.2%
48Inkling28.2%
49Hy327.3%
53GLM-4.725.0%
56Muse Spark24.3%
65GPT-5.115.6%