← All models

Tier-1 VCs on VCBench

Tier-1 VCs score F0.5 10.7 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 23.0% precision and 5.2% recall on the 4,500-founder private test set. That is rank 32 of 34.

Tier-1 VCs on the VCBench leaderboard today
Rank
#32 of 34
F0.5
10.7
Precision
23.0%
Recall
5.2%
Cost / 1k founders
n/a

Scored on the 4,500-founder private test set, mean over three folds. That is 1.0× the F0.5 of tier-1 VCs. See the full leaderboard.

Compared with the reference rows

EntryPrecisionRecallF0.5Cost / 1k
Tier-1 VCs23.0%5.2%10.7n/a
Think-Reason-Learn Ensemble40.6%30.1%37.9$0.87
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 the baseline was measured

A human baseline, not a model. Precision and recall come from real investment decisions reported in the VCBench paper: at the inception stage the market index reaches 1.9% precision, Y Combinator 3.2% and tier-1 venture firms 5.6%, with recall near 6% for both. The paper normalizes these to the dataset's 9% success rate, which gives the precision and F0.5 shown here, so humans and models are compared on the same base rate.

Read more

Frequently asked questions

How well do Tier-1 VCs predict founder success on VCBench?
Tier-1 VCs scores F0.5 10.7 on VCBench, with 23.0% precision and 5.2% recall, rank 32 of 34 as of 2026-10-26.
How was the Tier-1 VCs baseline measured?
A human baseline, not a model. Precision and recall come from real investment decisions reported in the VCBench paper: at the inception stage the market index reaches 1.9% precision, Y Combinator 3.2% and tier-1 venture firms 5.6%, with recall near 6% for both. The paper normalizes these to the dataset's 9% success rate, which gives the precision and F0.5 shown here, so humans and models are compared on the same base rate.
Does AI beat Tier-1 VCs on VCBench?
Yes. Think-Reason-Learn Ensemble (Vela + Oxford) leads with F0.5 37.9, 3.5 times the Tier-1 VCs score, and most LLM entries also score above it.