GPT-4o on VCBench
GPT-4o scores F0.5 25.7 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 30.0% precision and 16.3% recall on the 4,500-founder private test set. That is rank 15 of 32, 2.4× the F0.5 of tier-1 VCs and 3.0× Y Combinator, at $1.55 per 1,000 founders scored.
- Rank
- #15 of 32
- F0.5
- 25.7
- Precision
- 30.0%
- Recall
- 16.3%
- Cost / 1k founders
- $1.55
Scored on the 4,500-founder private test set, mean over three folds. That is 2.4× the F0.5 of tier-1 VCs. See the full leaderboard.
Compared with the reference rows
| Entry | Precision | Recall | F0.5 | Cost / 1k |
|---|---|---|---|---|
| GPT-4o | 30.0% | 16.3% | 25.7 | $1.55 |
| Think-Reason-Learn Ensemble | 40.6% | 30.1% | 37.9 | $0.87 |
| Tier-1 VCs | 23.0% | 5.2% | 10.7 | n/a |
| Y Combinator | 14.0% | 6.9% | 8.6 | n/a |
| Random Classifier | 9.0% | 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. GPT-4o used about 284 input and 84 output tokens per founder on gpt-4o, estimated from the prompt and the saved responses; reasoning models are assumed to think about 1,000 tokens per founder. Cost is tokens times the provider's list price on 2026-09-24 ($2.5 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
- Introducing VCBench, the First Benchmark for Venture Capital: VCBench, the first benchmark for venture capital, tests LLMs and human investors on predicting founder success across 9,000 anonymized profiles.
Frequently asked questions
- What does GPT-4o score on VCBench?
- GPT-4o scores F0.5 25.7 on VCBench, with 30.0% precision and 16.3% recall, rank 15 of 32 as of 2026-10-07.
- Does GPT-4o beat human investors at predicting founder success?
- Yes. Its F0.5 is 2.4 times that of tier-1 VCs (10.7) and 3.0 times Y Combinator (8.6), after both are normalized to the dataset's 9% base rate.
- How much does GPT-4o cost per 1,000 founders?
- About $1.55 per 1,000 founders at list prices on 2026-09-24. An LLM reads each founder profile at scoring time and returns a prediction. GPT-4o used about 284 input and 84 output tokens per founder on gpt-4o, estimated from the prompt and the saved responses; reasoning models are assumed to think about 1,000 tokens per founder. Cost is tokens times the provider's list price on 2026-09-24 ($2.5 input and $10 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.