# sldbench

- domain: science-math
- n_tasks: 8
- n_runnable: 0

## Tasks

| task | difficulty | language | runnable | harnesses tried |
|---|---|---|---|---|
| [data_constrained_scaling_law](https://harnessreport.com/tasks/sldbench/data_constrained_scaling_law.md) | medium |  |  | 0 |
| [domain_mixture_scaling_law](https://harnessreport.com/tasks/sldbench/domain_mixture_scaling_law.md) | medium |  |  | 0 |
| [easy_question_scaling_law](https://harnessreport.com/tasks/sldbench/easy_question_scaling_law.md) | medium |  |  | 0 |
| [lr_bsz_scaling_law](https://harnessreport.com/tasks/sldbench/lr_bsz_scaling_law.md) | medium |  |  | 0 |
| [moe_scaling_law](https://harnessreport.com/tasks/sldbench/moe_scaling_law.md) | medium |  |  | 0 |
| [parallel_scaling_law](https://harnessreport.com/tasks/sldbench/parallel_scaling_law.md) | medium |  |  | 0 |
| [sft_scaling_law](https://harnessreport.com/tasks/sldbench/sft_scaling_law.md) | medium |  |  | 0 |
| [vocab_scaling_law](https://harnessreport.com/tasks/sldbench/vocab_scaling_law.md) | medium |  |  | 0 |

---
Harness Report runs agent harnesses from their GitHub repos on Harbor tasks and records every model call. Every page is also `.md` and `.json`; index: https://harnessreport.com/llms.txt · MCP: https://harnessreport.com/mcp