← All models

Claude Sonnet 5 on VCBench

Claude Sonnet 5 scores F0.5 27.7 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 69.3% precision and 8.1% recall on the 4,500-founder private test set. That is rank 13 of 34, 2.6× the F0.5 of tier-1 VCs and 3.2× Y Combinator, at $2.20 per 1,000 founders scored.

Claude Sonnet 5 on the VCBench leaderboard today
Rank
#14 of 34
F0.5
27.7
Precision
69.3%
Recall
8.1%
Cost / 1k founders
$2.20

Scored on the 4,500-founder private test set, mean over three folds. That is 2.6× the F0.5 of tier-1 VCs. See the full leaderboard.

Compared with the reference rows

EntryPrecisionRecallF0.5Cost / 1k
Claude Sonnet 569.3%8.1%27.7$2.20
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

An LLM reads each founder profile at scoring time and returns a prediction. Claude Sonnet 5 used about 450 input and 130 output tokens per founder on claude-sonnet-5, measured from the API usage fields. Cost is tokens times the provider's list price on 2026-09-24 ($2 input and $10 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.

Read more

Frequently asked questions

What does Claude Sonnet 5 score on VCBench?
Claude Sonnet 5 scores F0.5 27.7 on VCBench, with 69.3% precision and 8.1% recall, rank 13 of 34 as of 2026-10-26.
Does Claude Sonnet 5 beat human investors at predicting founder success?
Yes. Its F0.5 is 2.6 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 Claude Sonnet 5 cost per 1,000 founders?
About $2.20 per 1,000 founders at list prices on 2026-09-24. An LLM reads each founder profile at scoring time and returns a prediction. Claude Sonnet 5 used about 450 input and 130 output tokens per founder on claude-sonnet-5, measured from the API usage fields. Cost is tokens times the provider's list price on 2026-09-24 ($2 input and $10 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.