New: GPT-6.2 benchmark report is here.Read the report ↗

Best LLMs on GDPval v2 (Internal)

GDPval v2 (Internal)

Real multistep consulting, finance, and design assignments.

Updated: Data as of:
Limited reportingNot saturated
Official benchmark
GDPval v2 (Internal) results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creatorVersionReported score
GPT-6.2 AstraOpenAI · Proprietary2 / OpenAI GPT-6.2 launch50.4%
GPT-6.2 SolOpenAI · Proprietary2 / OpenAI GPT-6.2 launch46.9%
View all 10 published reports