Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
General AI Assistant Tasks on GAIA Level 1 (val)
Loading...
62.3
Accuracy
GPT-5
21.116
31.808
42.5
53.192
Dec 7, 2025
Accuracy
95% CI
Between-Subject Variance
ICC
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
95% CI
Between-Subject Variance
ICC
GPT-5
Model=GPT-5, Web searc...
2025.12
62.3
-
0.185
0.774
GPT-4o
Model=GPT-4o, Web sear...
2025.12
22.7
-
0.1
0.561
Feedback
Search any
task
Search any
task