# mlgym-bench-hub

- domain: ml-research
- n_tasks: 12
- n_runnable: 0
- owner_org: Meta
- grading: tests
- task_kind: open-ended ML research tasks in a Gym env (CV, NLP, RL, game theory)
- url_repo: https://github.com/facebookresearch/MLGym
- url_paper: https://arxiv.org/abs/2502.14499

## Tasks

| task | difficulty | language | runnable | harnesses tried |
|---|---|---|---|---|
| [mlgym-battle-of-sexes](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-battle-of-sexes.md) | easy |  |  | 0 |
| [mlgym-blotto](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-blotto.md) | easy |  |  | 0 |
| [mlgym-image-classification-cifar10](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-image-classification-cifar10.md) | easy |  |  | 0 |
| [mlgym-image-classification-cifar10-l1](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-image-classification-cifar10-l1.md) | easy |  |  | 0 |
| [mlgym-image-classification-f-mnist](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-image-classification-f-mnist.md) | easy |  |  | 0 |
| [mlgym-prisoners-dilemma](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-prisoners-dilemma.md) | easy |  |  | 0 |
| [mlgym-regression-kaggle-house-price](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-regression-kaggle-house-price.md) | easy |  |  | 0 |
| [mlgym-regression-kaggle-house-price-l1](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-regression-kaggle-house-price-l1.md) | easy |  |  | 0 |
| [mlgym-rl-meta-maze-misc](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-rl-meta-maze-misc.md) | easy |  |  | 0 |
| [mlgym-rl-mountain-car-continuous](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-rl-mountain-car-continuous.md) | easy |  |  | 0 |
| [mlgym-rl-mountain-car-continuous-reinforce](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-rl-mountain-car-continuous-reinforce.md) | easy |  |  | 0 |
| [mlgym-titanic](https://harnessreport.com/tasks/mlgym-bench-hub/mlgym-titanic.md) | easy |  |  | 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