List your company

General AI Assistant Tasks on GAIA Level 1 (val)

62.3AccuracyGPT-5
21.11631.80842.553.192Dec 7, 2025

Evaluation results

MethodLinks
GPT-5Model=GPT-5, Web search=true, Trials per question=642025.1262.3—0.1850.774
GPT-4oModel=GPT-4o, Web search=true, Trials per question=642025.1222.7—0.10.561