Research using VCBench.
Work by other groups that cites the benchmark or was scored on it. If you publish with VCBench or submit a model, email benchmark@vela.partners and we will list it here.
Investinor Linear v1
Investinor. A linear classical-ML model submitted by the Norwegian state investment company. No LLM at scoring time; the best classical entry on the board.
Evaluation and success rate prediction of innovation and entrepreneurship projects using a group recommendation algorithm
Yan Hou, Shuling Yang (Jilin Normal University, Discover Internet of Things). Cites VCBench as the reference benchmark for AI prediction of venture outcomes.
GemVC-v0
Madhusudhana Naidu (Independent). A Gemini 2.5 Flash reasoning entry submitted by an independent researcher.
Pvalyou Founder Model (ML)
Itay Attar (Pvalyou). A classical-ML founder model submitted by Pvalyou; no LLM at scoring time.
AI as the New Mentor
Scott Ford (University of Colorado Boulder, IGI Global). Book chapter citing VCBench on how AI compares with expert investors at judging founders.
Predicting Founder Success Without an LLM: An Interpretable Tree-Based Approach to VCBench
Maheni Soumah, Jessica Mbounkap, Habiba Djigo (aivancity School for Technology, Business & Society, Cambridge Open Engage). Trains interpretable tree models on the VCBench profiles with no LLM at scoring time.
FinGPT-VC: Financial Large Language Models for Founder Success Prediction in Venture Capital
Jingyu Huang, Sitong Zhu, James Tang, Xiao-Yang Liu (Columbia University, IEEE IDS 2026). Fine-tunes financial LLMs on VCBench; FinGPT-VC1 and FinGPT-VC2 are on the leaderboard. On the board: FinGPT-VC1, FinGPT-VC2.
When Career Data Runs Out: Structured Feature Engineering and Signal Limits for Founder Success
Yagiz Ihlamur (Independent, IEEE IDS 2026). Structured features and a rule stump on VCBench; Structured-Rule-Stump is on the leaderboard. On the board: Structured-Rule-Stump.
Prompt Engineering for Venture Capital Founder Success Prediction: A Systematic Evaluation on VCBench
Tasnim Masheh (Independent, SSRN). Compares prompt designs for LLM founder scoring on VCBench.