YC-Bench: leaderboard
Mean final funds in thousands of dollars after a simulated startup’s one-year horizon over three seeds. Retains the primary monthly-data precision and explicit source checkpoint and reasoning settings, starting from $200,000.
Metric: Mean Final Funds ($K). Source: collinear-ai.github.io. Saturation forecast: Around December 2027. 53 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 2873.73 | #3 |
| 2 | Grok 4.5 | 2629.9 | #48 |
| 3 | Qwen 3.8 Max | 2095.84 | #35 |
| 4 | Kimi K3 | 2053.3 | #30 |
| 5 | Claude Fable 5 | 1977.57 | #16 |
| 6 | Claude Opus 5 | 1911.59 | #12 |
| 7 | Claude Sonnet 5.5 | 1741.31 | #11 |
| 8 | Claude Opus 4.7 | 1714.51 | #49 |
| 9 | Claude Opus 4.8 | 1711.39 | #37 |
| 10 | Grok 4.7 | 1666.39 | #25 |
| 11 | DeepSeek V4.1 Flash | 1657.24 | #36 |
| 12 | Grok 4.6 | 1568.24 | #26 |
| 13 | GLM-5.1 | 1510.77 | #97 |
| 14 | DeepSeek V4 Pro (0813) | 1459.74 | #53 |
| 15 | GPT-6 Sol | 1441.79 | #14 |
No result here: #8 Gemini 4 Argon, #9 Claude Fable 5.1, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=yc-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.