| - dataset: | |
| id: collinear-ai/yc-bench | |
| task_id: medium | |
| value: 1208190 | |
| date: "2026-03-24" | |
| source: | |
| url: https://github.com/collinear-ai/yc-bench | |
| name: "YC-Bench eval" | |
| notes: "avg final funds (USD) across seeds 1,2,3. GLM-5 (via OpenRouter z-ai/glm-5)" | |
| - dataset: | |
| id: collinear-ai/yc-bench | |
| task_id: medium | |
| value: 1208190 | |
| date: "2026-03-24" | |
| source: | |
| url: https://github.com/collinear-ai/yc-bench | |
| name: "YC-Bench eval" | |
| notes: "avg final funds (USD) across seeds 1,2,3. GLM-5 (via OpenRouter z-ai/glm-5)" | |