{
 "id": "benchpress/results-multi-temp-seed",
 "owner": "benchpress",
 "name": "results-multi-temp-seed",
 "downloads": 37,
 "likes": 0,
 "last_modified": "2026-06-07T16:41:52.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "These results were produced by evaluating the models below on the\nfollowing public benchmarks via `lm-evaluation-harness`. Each benchmark\nremains under its own license; the table records the exact upstream\nHugging Face dataset and its license. **Note the multilingual subsets\nare non-commercial (CC BY-NC 4.0).**\n\n| Benchmark group | Setting(s) | Upstream dataset | License |\n| --- | --- | --- | --- |\n| `arc` | en_easy, en_challenge | [`allenai/ai2_arc`](https://huggingface.co/datasets/allenai/ai2_arc) | CC BY-SA 4.0 |\n| `arc` | es, ar, hi, ru (multilingual) | [`alexandrainst/m_arc`](https://huggingface.co/datasets/alexandrainst/m_arc) | CC BY-NC 4.0 (non-commercial) |\n| `hellaswag` | en | [`Rowan/hellaswag`](https://huggingface.co/datasets/Rowan/hellaswag) | MIT |\n| `hellaswag` | es, ar, hi, ru (multilingual) | [`alexandrainst/m_hellaswag`](https://huggingface.co/datasets/alexandrainst/m_hellaswag) | CC BY-NC 4.0 (non-commercial) |\n| `truthfulqa_mc2` | en | [`truthfulqa/truthful_qa`](https://huggingface.co/datasets/truthfulqa/truthful_qa) | Apache-2.0 |\n| `truthfulqa_mc2` | es, ar, hi, ru (multilingual) | [`alexandrainst/m_truthfulqa`](https://huggingface.co/datasets/alexandrainst/m_truthfulqa) | CC BY-NC 4.0 (non-commercial) |\n| `gsm8k_cot` | en | [`openai/gsm8k`](https://huggingface.co/datasets/openai/gsm8k) | MIT |\n| `mgsm_en_cot` | en, es, fr, de, ru, zh, ja, bn, sw, te, th (multilingual) | [`juletxara/mgsm`](https://huggingface.co/datasets/juletxara/mgsm) | CC BY-SA 4.0 |\n",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "4365c367496450c006551d5ec93eb2c20ca6da56",
 "stated_evidence": "https://huggingface.co/datasets/benchpress/results-multi-temp-seed/blob/4365c367496450c006551d5ec93eb2c20ca6da56/README.md",
 "file_evidence": "https://huggingface.co/datasets/benchpress/results-multi-temp-seed/tree/4365c367496450c006551d5ec93eb2c20ca6da56",
 "card_nc": false
}