GPT-4o-mini on VCBench
GPT-4o-mini scores F0.5 23.0 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 31.5% precision and 11.1% recall on the 4,500-founder private test set. That is rank 19 of 32, 2.1× the F0.5 of tier-1 VCs and 2.7× Y Combinator, at $0.09 per 1,000 founders scored.
- Rank
- #19 of 32
- F0.5
- 23.0
- Precision
- 31.5%
- Recall
- 11.1%
- Cost / 1k founders
- $0.09
Scored on the 4,500-founder private test set, mean over three folds. That is 2.1× 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-mini | 31.5% | 11.1% | 23.0 | $0.09 |
| 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-mini used about 284 input and 82 output tokens per founder on gpt-4o-mini, 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 ($0.15 input and $0.6 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-mini score on VCBench?
- GPT-4o-mini scores F0.5 23.0 on VCBench, with 31.5% precision and 11.1% recall, rank 19 of 32 as of 2026-10-07.
- Does GPT-4o-mini beat human investors at predicting founder success?
- Yes. Its F0.5 is 2.1 times that of tier-1 VCs (10.7) and 2.7 times Y Combinator (8.6), after both are normalized to the dataset's 9% base rate.
- How much does GPT-4o-mini cost per 1,000 founders?
- About $0.09 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-mini used about 284 input and 82 output tokens per founder on gpt-4o-mini, 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 ($0.15 input and $0.6 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.