Claude Haiku 4.5 on VCBench
Claude Haiku 4.5 scores F0.5 22.6 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 21.2% precision and 30.1% recall on the 4,500-founder private test set. That is rank 20 of 32, 2.1× the F0.5 of tier-1 VCs and 2.6× Y Combinator, at $0.97 per 1,000 founders scored.
- Rank
- #20 of 32
- F0.5
- 22.6
- Precision
- 21.2%
- Recall
- 30.1%
- Cost / 1k founders
- $0.97
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 |
|---|---|---|---|---|
| Claude Haiku 4.5 | 21.2% | 30.1% | 22.6 | $0.97 |
| 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. Claude Haiku 4.5 used about 315 input and 130 output tokens per founder on claude-haiku-4-5, measured from the API usage fields. Cost is tokens times the provider's list price on 2026-09-24 ($1 input and $5 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.
Frequently asked questions
- What does Claude Haiku 4.5 score on VCBench?
- Claude Haiku 4.5 scores F0.5 22.6 on VCBench, with 21.2% precision and 30.1% recall, rank 20 of 32 as of 2026-10-07.
- Does Claude Haiku 4.5 beat human investors at predicting founder success?
- Yes. Its F0.5 is 2.1 times that of tier-1 VCs (10.7) and 2.6 times Y Combinator (8.6), after both are normalized to the dataset's 9% base rate.
- How much does Claude Haiku 4.5 cost per 1,000 founders?
- About $0.97 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 Haiku 4.5 used about 315 input and 130 output tokens per founder on claude-haiku-4-5, measured from the API usage fields. Cost is tokens times the provider's list price on 2026-09-24 ($1 input and $5 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.