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 18
values | reasonings large_stringlengths 2 12.6k | observations large_stringlengths 2 12.9k | screens large_stringlengths 93 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 15
values | verdict large_stringclasses 3
values |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
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 | |||||
1025e14dc940440db997fec9429c8273 | a | 0 | 2026-08-07T20:35:57.321898+00:00 | mteb/results | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset (mteb/results) is a multilingual benchmark containing model evaluation results for German (deu-Latn) using the thenlper/gte-large-zh model across MassiveIntentClassification, MTOPDomainClassification, and FalseFriendsGermanEnglish tasks, providing a comprehensive assessment of cross-lingual text understand... | 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 \"mteb/results\" 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 making my conclusion.\n\nLet me sta... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"mteb/results\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "TOOL_ERROR: HTTPError: 404 Client Error: Not Found for... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 33, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": []} | 5 | pass | |||||
1d4234a8d6b445fda99608d291fe5611 | a | 0 | 2026-08-05T20:55:24.407754+00:00 | DatPySci/OpenThoughts-114k-preprocessed | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | DatPySci/OpenThoughts-114k-preprocessed is a preprocessed collection of 114k mathematical problems from numina_math, featuring inequality proofs, polynomial analyses, and geometry challenges in English, designed for advanced mathematical reasoning. | 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 \"DatPySci/OpenThoughts-114k-preprocessed\" 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 ... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"DatPySci/OpenThoughts-114k-preprocessed\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "TOOL_ERROR: HTTPError: 404 ... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 26, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "114k", "normalized": "114000", "badge": "ok", "sources": [{"obs_index": 0, "tool": "splits", "op": null, "partial": false}, {"obs_index": 1, "tool": "s... | 3 | good | 2026-08-05T21:01:25.097565+00:00 | pass | |||
1c7221c531144878ad783c25c0bcb461 | a | 0 | 2026-08-07T16:12:54.277650+00:00 | mah-asd/eval-videos | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The mah-asd/eval-videos dataset consists of eval rollout videos from Behavior-1K radio residual experiments (instances 301–306), sourced from the Mah-ASD collection, designed for evaluating model performance on these specific instances. | 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... | # eval-videos
Eval rollout videos from Behavior-1K / radio residual experiments (instances 301–306 and related).
Videos are organized as:
```
runs/<run_tag>/<scale_or_mode>/.../videos/*.mp4
``` | ["The user wants me to write a single sentence (max 50 words) describing what the dataset \"mah-asd/eval-videos\" 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 TLDR.\n\n... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"mah-asd/eval-videos\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "linked_papers", "op": "", "content": "No papers linked to this dataset.", "coverag... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 29, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "1K", "normalized": "1000", "badge": "ok", "sources": [{"obs_index": 2, "tool": "sample_rows", "op": null, "partial": false}, {"obs_index": 2, "tool": "... | 4 | pass | ||||
42fa0e1466a340bdbaa628dad8bce712 | a | 0 | 2026-08-06T14:44:15.295385+00:00 | iambatinusak/test_dataset | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The iambatinusak/test_dataset is a Turkish-language coding instruction dataset containing programming tasks and solutions, primarily used for training models on technical problem-solving in Turkish. | 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 is and its characteristics based on the provided information. The dataset ID is \"iambatinusak/test_dataset\". I need to use the available tools to gather information about this dataset before making my conclusion.\n\nLet me start... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"iambatinusak/test_dataset\", \"config\": \"default\", \"split\": \"train\"}, {\"dataset\": \"iambatinusak/test_dataset\", \"config\": \"default\", \"split\": \"test\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_inde... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 23, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": []} | 5 | pass | |||||
561ac3da341049af9c658907bb201a23 | a | 0 | 2026-08-06T09:49:47.422703+00:00 | mneb/wnut2017 | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | mneb/wnut2017 is a news article corpus with annotated named entity recognition (person, location, corporation) across train, validation, and test splits, designed for NER tasks in English. | 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 \"mneb/wnut2017\" is about - covering domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the available tools to get information about this dataset before writing the TLDR.\n\nLet me star... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"mneb/wnut2017\", \"config\": \"default\", \"split\": \"train\"}, {\"dataset\": \"mneb/wnut2017\", \"config\": \"default\", \"split\": \"validation\"}, {\"dataset\": \"mneb/wnut2017\", \"config\": \"default\", \"split\": \"test\"}], ... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 26, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "2017", "normalized": "2017", "badge": "ok", "sources": [{"obs_index": 0, "tool": "splits", "op": null, "partial": false}, {"obs_index": 0, "tool": "spl... | 5 | pass | |||||
5baf4981046e456abe9e21afc7094dfc | a | 0 | 2026-08-12T12:25:18.028216+00:00 | nuuuwan/lk-dmc-weather-forecasts-chunks | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset contains Sri Lankan weather forecast and advisory records in Tamil and Sinhala, spanning 2023-2026, with each chunk representing a weather bulletin including forecasts, warnings, and advisories for coastal regions. | 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\": \"nuuuwan/lk-dmc-weather-forecasts-chunks\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "{\"num_examples\": 15112, \... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 31, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "2023", "normalized": "2023", "badge": "ok", "sources": [{"obs_index": 1, "tool": "statistics", "op": null, "partial": false}, {"obs_index": 1, "tool": ... | 3 | pass | |||||
5ccabc0736994dab97ed6488de6b11f6 | a | 0 | 2026-08-07T07:21:06.288661+00:00 | biglam/sloane-catalogues | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | The Sloane Manuscript Index Cards Dataset comprises digitized handwritten index cards from the British Library's Sloane Manuscript collection, providing archival catalog records with author names, manuscript titles, shelfmarks, and cross-references for OCR and VLM benchmarking. | 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... | # Sloane Manuscript Index Cards Dataset
## Dataset Description
This dataset contains digitized index cards from the British Library's Sloane Manuscript collection. The cards represent a catalog system used to index the Sloane manuscripts, one of the founding collections of the British Museum (now British Library).
#... | ["The user wants me to write ONE sentence (max 50 words) describing what this dataset is and its purpose, based on the provided card information. I need to:\n1. Ground my answer with tools - first check splits, then get statistics or sample rows to understand the dataset better\n2. Make sure every claim comes from the ... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"biglam/sloane-catalogues\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "TOOL_ERROR: HTTPError: 404 Client Error: N... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 35, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": []} | 4 | 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 | |||||
31acd22e6f6743a78aaf3255d2b2a40b | a | 0 | 2026-08-06T06:58:46.532025+00:00 | CyanMonkey/Dataset-2 | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset is a mixed pretraining corpus containing 500,000 rows designed for language model training, providing diverse text data across multiple domains. | 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... | # Dataset
Mixed pretraining corpus - 500,000 rows, 1 shards. | ["The user wants me to write a single sentence (max 50 words) describing what this dataset is, including its domain, data source/provenance, method, languages, and distinctive capabilities. I need to use the tools to get information about this dataset before providing the TLDR.\n\nLet me start by calling the splits fun... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"CyanMonkey/Dataset-2\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "{\"num_examples\": 500000, \"statistics\": [{\... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 22, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "500,000", "normalized": "500000", "badge": "ok", "sources": [{"obs_index": 1, "tool": "statistics", "op": null, "partial": false}, {"obs_index": null, ... | 4 | pass | ||||
3473375e0f484439b24c30dde782e71e | a | 0 | 2026-08-05T20:01:53.998448+00:00 | wannaphong/thai-openbase-instruction | single | endpoint | LiquidAI/LFM2.5-2.6B | main | 0 | This dataset, wannaphong/thai-openbase-instruction, is an AI instruction-tuning collection for Thai language derived from openbase.in.th, containing 10,128 training examples with two-message conversations per entry, enabling Thai-language instruction-following capabilities. | 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... | # Thai openbase instruction
AI gen instruction dataset from openbase.in.th | ["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 tools to gather information about this dataset before providing the TLDR.\n\nLet me start by checking the splits and basi... | [{"obs_index": 0, "tool": "splits", "op": "", "content": "{\"splits\": [{\"dataset\": \"wannaphong/thai-openbase-instruction\", \"config\": \"default\", \"split\": \"train\"}], \"pending\": [], \"failed\": []}", "coverage": ""}, {"obs_index": 1, "tool": "statistics", "op": "", "content": "{\"num_examples\": 10128, \"st... | {"verdict": "pass", "refusal": false, "format": {"pass": true, "words": 27, "one_sentence": true}, "meta_language": {"pass": true, "matches": []}, "numbers": [{"text": "10,128", "normalized": "10128", "badge": "ok", "sources": [{"obs_index": 1, "tool": "statistics", "op": null, "partial": false}, {"obs_index": 1, "tool... | 4 | meh | 2026-08-05T20:02:07.893234+00:00 | pass |
End of preview. Expand in Data Studio
No dataset card yet
- Downloads last month
- 344