GDPVal AA ELO
Agents
+
+
+
+
About
GDPVal AA ELO measures AI model performance on economically valuable professional work tasks across 44 occupations and 9 industries, scored via ELO ratings from blind pairwise comparisons using the Artificial Analysis evaluation harness on OpenAI's GDPval dataset.
+
+
+
+
Evaluation Stats
Total Models6
Organizations3
Verified Results0
Self-Reported6
+
+
+
+
Benchmark Details
Max Score2000
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
6 models
Top Score
81.7%
Average Score
71.6%
High Performers (80%+)
2Top Organizations
#1Anthropic
4 models
74.1%
#2OpenAI
1 model
73.1%
#3Google DeepMind
1 model
60.1%
+
+
+
+
Leaderboard
6 models ranked by performance on GDPVal AA ELO
| License | Links | ||||
|---|---|---|---|---|---|
| Feb 17, 2026 | Proprietary | 81.7% | |||
| Feb 1, 2026 | Proprietary | 80.3% | |||
| Dec 11, 2025 | Proprietary | 73.1% | |||
| Nov 1, 2025 | Proprietary | 70.8% | |||
| Sep 29, 2025 | Proprietary | 63.8% | |||
| Nov 18, 2025 | Proprietary | 60.1% |
