Claude Opus 5.5 on VCBench
Claude Opus 5.5 scores F0.5 24.7 on VCBench, the venture capital benchmark from the University of Oxford and Vela Research, with 77.7% precision and 6.7% recall on the 4,500-founder private test set. That is rank 17 of 32, 2.3× the F0.5 of tier-1 VCs and 2.9× Y Combinator, at $5.33 per 1,000 founders scored.
- Rank
- #17 of 32
- F0.5
- 24.7
- Precision
- 77.7%
- Recall
- 6.7%
- Cost / 1k founders
- $5.33
Scored on the 4,500-founder private test set, mean over three folds. That is 2.3× the F0.5 of tier-1 VCs. See the full leaderboard.
Compared with the reference rows
| Entry | Precision | Recall | F0.5 | Cost / 1k |
|---|---|---|---|---|
| Claude Opus 5.5 | 77.7% | 6.7% | 24.7 | $5.33 |
| 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 Opus 5.5 used about 452 input and 176 output tokens per founder on claude-opus-5-5, measured from the API usage fields. Cost is tokens times the provider's list price on 2026-09-24 ($4 input and $20 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.
Read more
- VCBench Leaderboard Update: Accuracy vs Cost, Plus GPT-6 and Claude Opus 5.5: VCBench now plots F0.5 against the cost of scoring 1,000 founders, with GPT-6, Claude Opus 5.5, new submissions and the Think-Reason-Learn Ensemble.
Frequently asked questions
- What does Claude Opus 5.5 score on VCBench?
- Claude Opus 5.5 scores F0.5 24.7 on VCBench, with 77.7% precision and 6.7% recall, rank 17 of 32 as of 2026-10-07.
- Does Claude Opus 5.5 beat human investors at predicting founder success?
- Yes. Its F0.5 is 2.3 times that of tier-1 VCs (10.7) and 2.9 times Y Combinator (8.6), after both are normalized to the dataset's 9% base rate.
- How much does Claude Opus 5.5 cost per 1,000 founders?
- About $5.33 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 Opus 5.5 used about 452 input and 176 output tokens per founder on claude-opus-5-5, measured from the API usage fields. Cost is tokens times the provider's list price on 2026-09-24 ($4 input and $20 output per million tokens), so it recomputes when prices change. Build costs such as question or policy generation are excluded.