← All models

large-founder-model-v0 on VCBench

large-founder-model-v0 scores F0.5 27.2 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 31.7% precision and 17.5% recall on the 4,500-founder private test set. That is rank 15 of 34, 2.5× the F0.5 of tier-1 VCs and 3.2× Y Combinator, at $0 per 1,000 founders scored.

large-founder-model-v0 on the VCBench leaderboard today
Rank
#15 of 34
F0.5
27.2
Precision
31.7%
Recall
17.5%
Cost / 1k founders
$0

Scored on the 4,500-founder private test set, mean over three folds. That is 2.5× the F0.5 of tier-1 VCs. See the full leaderboard.

Compared with the reference rows

EntryPrecisionRecallF0.5Cost / 1k
large-founder-model-v031.7%17.5%27.2$0
Think-Reason-Learn Ensemble40.6%30.1%37.9$0.87
Tier-1 VCs23.0%5.2%10.7n/a
Y Combinator14.0%6.9%8.6n/a
Random Classifier9.0%9.0%9.0$0

Human rows are normalized to the dataset's 9% success rate, so every entry is compared on the same base rate. Costs use list prices on 2026-09-24.

How it was scored

No LLM runs at scoring time. A trained model reads structured features from the anonymized profile (education, career history, prior companies) and scores the founder directly, so the API cost at scoring is $0. Training cost is excluded, the same rule applied to every entry.

Frequently asked questions

What does large-founder-model-v0 score on VCBench?
large-founder-model-v0 scores F0.5 27.2 on VCBench, with 31.7% precision and 17.5% recall, rank 15 of 34 as of 2026-10-26.
Does large-founder-model-v0 beat human investors at predicting founder success?
Yes. Its F0.5 is 2.5 times that of tier-1 VCs (10.7) and 3.2 times Y Combinator (8.6), after both are normalized to the dataset's 9% base rate.
How much does large-founder-model-v0 cost per 1,000 founders?
$0 at scoring time: no LLM runs when large-founder-model-v0 scores a founder. Training cost is excluded for every entry.