episode_id large_stringlengths 32 32 | gen large_stringclasses 1
value | position int64 0 0 | ts large_stringlengths 32 32 | dataset_id large_stringlengths 12 73 | mode large_stringclasses 1
value | backend large_stringclasses 1
value | model large_stringclasses 1
value | revision large_stringclasses 1
value | temperature float64 0 0 | tldr large_stringlengths 0 422 | terminal large_stringclasses 3
values | trajectory large_stringlengths 748 15.8k | card large_stringclasses 13
values | reasonings large_stringlengths 2 9.77k | observations large_stringlengths 2 12.9k | screens large_stringlengths 161 2.28k | n_turns int64 1 7 | coverage large_stringclasses 1
value | rating large_stringclasses 3
values | chosen_gen large_stringclasses 1
value | rated_ts large_stringclasses 14
values | verdict large_stringclasses 2
values |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
605f950c3d3e4e82a458443b6ae7321c | a | 0 | 2026-08-07T11:02:03.493432+00:00 | abanfalvi/eu_policies_sft | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset comprises English policy documents centered on the EU AI Act (Regulation (EU) 2024/1689), sourced from official EU regulatory materials, offering a distinctive capability for training language models on artificial intelligence governance and compliance requirements. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what the dataset \"abanfalvi/eu_policies_sft\" is about - covering domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to gather information about this dataset before providing the TLD... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"abanfalvi/eu_policies_sft\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "TOOL_ERROR: HTTPError: 404 Client Error: ... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 36, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "2024", "normalized": "2024", "badge": "ok", "sources": [{"obs_index": 3, "tool": "sample_rows", "op": null, "partial": false}, {"obs_index": 3, "tool":... | 4 | pass | |||||
d2c734af4b0e4fd798864f6a7bc95e8e | a | 0 | 2026-08-05T20:18:31.887046+00:00 | Mozilla/query-intent-detection-dataset | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The Mozilla/query-intent-detection-dataset is a large-scale text classification dataset containing queries labeled as either 'Search' or 'Chat' for intent detection in conversational AI, sourced from Mozilla research, enabling models to distinguish between information-retrieval and chatbot interaction patterns. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what the dataset \"Mozilla/query-intent-detection-dataset\" is, covering:\n- Data source/provenance\n- Method\n- Languages\n- Distinctive capability\n\nI need to use the available tools to get information about this dataset. Let me start by checki... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"Mozilla/query-intent-detection-dataset\", \"config\": \"default\", \"split\": \"train\"}, {\"dataset\": \"Mozilla/query-intent-detection-dataset\", \"config\": \"default\", \"split\": \"validation\"}, {\"dataset\": \"Mozilla/query-i... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 36, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": []} | 5 | pass | |||||
7515bcefdf4a4c3e95216288a5d0b0de | a | 0 | 2026-08-07T01:36:02.656831+00:00 | huggingface/documentation-images | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The huggingface/documentation-images dataset contains curated images used in the documentation of HuggingFace's libraries, sourced directly from HuggingFace's model repository with optimized variants (FP32, quantized, torch, overview) across train/validation/test splits. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ### This dataset contains images used in the documentation of HuggingFace's libraries.
HF Team: Please make sure you optimize the assets before uploading them.
My favorite tool for this is https://tinypng.com/. | ["The user wants me to write a single sentence (max 50 words) describing what the dataset \"huggingface/documentation-images\" is about - its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the tools to gather information about this dataset before providing the TLDR.\n\nLe... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"huggingface/documentation-images\", \"config\": \"default\", \"split\": \"train\"}, {\"dataset\": \"huggingface/documentation-images\", \"config\": \"default\", \"split\": \"validation\"}, {\"dataset\": \"huggingface/documentation-i... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 29, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "32,", "normalized": "32", "badge": "ok", "sources": [{"obs_index": 2, "tool": "sample_rows", "op": null, "partial": false}]}]} | 4 | pass | ||||
3728521e83c147519b31a9468b3ac778 | a | 0 | 2026-08-07T05:50:10.160894+00:00 | Sachin21112004/news-entertainment-dataset | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The Sachin21112004/news-entertainment-dataset is an English-language news entertainment dataset sourced from Variety and Deadline feeds, containing 18,564 articles primarily categorized as entertainment. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what this dataset is - its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to gather information about the dataset first.\n\nLet me start by checking the splits and statistics for ... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"Sachin21112004/news-entertainment-dataset\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "{\"num_examples\": 18564,... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 21, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "21112004", "normalized": "2.1112e+07", "badge": "ok", "sources": [{"obs_index": 0, "tool": "splits", "op": null, "partial": false}, {"obs_index": null,... | 3 | pass | |||||
a06a399e27d644ef8d01b454d5cdfb3b | a | 0 | 2026-08-07T10:26:51.423765+00:00 | iantc104/hsl_leap_grasp_lightbulb_rrt_filtered_v1 | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset contains 499,679 example frames for evaluating robotic grasping of lightbulb objects, featuring query boxes, object poses, target positions, and contact information, derived from sim-to-real transfer research using RRT-based planning methods. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what this dataset is - its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to gather information about the dataset before making my statement.\n\nLet me start by checking the split... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"iantc104/hsl_leap_grasp_lightbulb_rrt_filtered_v1\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "{\"num_examples\"... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 32, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "499,679", "normalized": "499679", "badge": "ok", "sources": [{"obs_index": 1, "tool": "statistics", "op": null, "partial": false}, {"obs_index": 1, "to... | 5 | pass | |||||
91c20b049aaf43589492bba1083ccc72 | a | 0 | 2026-08-07T16:11:23.727938+00:00 | fzzhang/qwen3_8b_coding_depth4v3_probval_instill_n8_valredundancy5_round1 | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset (fzzhang/qwen3_8b_coding_depth4v3_probval_instill_n8_valredundancy5_round1) is a training split containing 31,218 examples, each with exactly two messages, focused on coding and probability tasks. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what this dataset is - its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to gather information about this dataset before making my conclusion.\n\nLet me start by checking the spl... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"fzzhang/qwen3_8b_coding_depth4v3_probval_instill_n8_valredundancy5_round1\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "cont... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 21, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "3", "normalized": "3", "badge": "ok", "sources": [{"obs_index": 0, "tool": "splits", "op": null, "partial": false}, {"obs_index": 0, "tool": "splits", ... | 4 | good | 2026-08-07T16:12:02.949565+00:00 | pass | |||
b6c265dbcd6943579eb45c3e13dfc549 | a | 0 | 2026-08-06T23:32:21.914148+00:00 | keystats/lingala-asr | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The keystats/lingala-asr dataset is a Lingala-language Automatic Speech Recognition (ASR) collection with audio recordings and text transcriptions, providing train and validation splits for training and evaluating speech-to-text models in Lingala. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what the dataset \"keystats/lingala-asr\" is about - its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to gather information about this dataset before providing the TLDR.\n\nLet ... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"keystats/lingala-asr\", \"config\": \"default\", \"split\": \"train\"}, {\"dataset\": \"keystats/lingala-asr\", \"config\": \"default\", \"split\": \"validation\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": ... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 30, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": []} | 5 | pass | |||||
f639b5312e014c44ac19f49f887eeb7c | a | 0 | 2026-08-07T14:07:19.423202+00:00 | laion/dev_set_v2_a1_crosscodeeval_typescript_20260805_125428 | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset (laion/dev_set_v2_a1_crosscodeeval_typescript_20260805_125428) is a TypeScript-focused cross-code evaluation set containing 3,045 examples with conversation and metadata fields, designed for assessing code generation across programming languages. | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what this dataset is - its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to gather information about this dataset before making my conclusion.\n\nLet me start by checking the spl... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"laion/dev_set_v2_a1_crosscodeeval_typescript_20260805_125428\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "{\"num... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 25, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "2", "normalized": "2", "badge": "ok", "sources": [{"obs_index": 0, "tool": "splits", "op": null, "partial": false}, {"obs_index": 1, "tool": "statistic... | 3 | pass | |||||
4502cfc0cef34b77b50b465620f7ad5e | a | 0 | 2026-08-07T14:12:17.786834+00:00 | jablonkagroup/sfm-synthetic-data | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The dataset jablonkagroup/sfm-synthetic-data is a collection of synthetic spectral data (likely from solid-state microscopy) designed for anomaly detection, organized into configs such as anomalous_gc, anomalous_hnmr, and others across five case splits, with each row containing spectral measurements and an anomaly flag... | submit | [{"role": "user", "content": "Write ONE sentence (max 50 words, English) saying what this dataset is and what it is\nfor: domain, data source/provenance, method, languages, distinctive capability when stated.\nDo not restate license, popularity, or usage instructions. Do not invent anything \u2014 every claim\nmust com... | ["The user wants me to write a single sentence (max 50 words) describing what the dataset \"jablonkagroup/sfm-synthetic-data\" is, covering:\n- Data source/provenance\n- Method\n- Languages\n- Distinctive capability\n\nI need to use the available tools to gather information about this dataset before writing the TLDR. L... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"jablonkagroup/sfm-synthetic-data\", \"config\": \"anomalous_gc\", \"split\": \"case_1\"}, {\"dataset\": \"jablonkagroup/sfm-synthetic-data\", \"config\": \"anomalous_gc\", \"split\": \"case_2\"}, {\"dataset\": \"jablonkagroup/sfm-sy... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 46, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": []} | 4 | pass | |||||
5993b4b2d5f34e25be7a9823c5a4d69e | a | 0 | 2026-08-07T08:31:45.708076+00:00 | cedy243/uploadm8-content-success-v1 | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | "This dataset contains YouTube automotive short-form videos with metadata including captions, hashta(...TRUNCATED) | submit | "[{\"role\": \"user\", \"content\": \"Write ONE sentence (max 50 words, English) saying what this da(...TRUNCATED) | "[\"The user wants me to write a single sentence (max 50 words) describing what the dataset is and i(...TRUNCATED) | "[{\"obs_index\": 0, \"tool\": \"splits\", \"op\": \"\", \"content\": \"{\\\"splits\\\": [{\\\"datas(...TRUNCATED) | "{\"verdict\": \"pass\", \"refusal\": false, \"format\": {\"pass\": true, \"words\": 21, \"one_sente(...TRUNCATED) | 6 | pass |
End of preview. Expand in Data Studio
No dataset card yet
- Downloads last month
- 45