Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
699
751
answer
stringclasses
1 value
task_config
stringclasses
1 value
task_source
stringclasses
1 value
prompt
listlengths
1
1
model_responses
listlengths
0
0
model_responses__eval_is_correct
listlengths
0
0
all_other_columns
stringlengths
176
228
original_split
stringclasses
1 value
metadata
null
model_responses__best_of_n_atags
listlengths
4
4
model_responses__best_of_n_atags__finish_reason_length_flags
listlengths
4
4
model_responses__best_of_n_atags__length_partial_responses
listlengths
4
4
prompt__best_of_n_atags__metadata
stringlengths
1.1k
1.15k
model_responses__best_of_n_atags__metadata
stringclasses
1 value
model_responses__best_of_n_atags__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__eval_extraction_metadata
stringlengths
234
605
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
400
830
model_responses__best_of_n_atags__internal_answers__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__internal_answers__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata
stringlengths
378
3.25k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
332
3.25k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-10-27 00:00:00
2025-10-27 00:00:00
answer_index
null
answer_key
null
choices
null
id
null
difficulty
null
domain
null
evaluation_type
null
expected_answer_format
null
original_answer
null
source
null
task_type
null
variant
null
acronym
stringlengths
5
5
formed_acronym
stringlengths
5
5
word_count
int64
5
8
words
listlengths
5
8
length
null
letters
null
question_idx
int64
0
143
response_idx
int64
0
3
original_response_idx_in_16
int64
0
3
original_response
stringlengths
4.73k
62.3k
budget_forced_continuations
dict
model_responses__budget_forced
listlengths
2
4
model_responses__budget_forced__eval_is_correct
listlengths
2
4
model_responses__budget_forced__eval_extracted_answers
listlengths
2
4
model_responses__budget_forced__eval_extraction_metadata
stringlengths
120
2.6k
model_responses__budget_forced__eval_evaluation_metadata
stringlengths
400
4.32k
model_responses__budget_forced__internal_answers__eval_is_correct
listlengths
2
4
model_responses__budget_forced__internal_answers__eval_extracted_answers
listlengths
2
4
model_responses__budget_forced__internal_answers__eval_extraction_metadata
stringlengths
198
7.83k
model_responses__budget_forced__internal_answers__eval_evaluation_metadata
stringlengths
188
7.01k
model_responses__budget_forced__metrics
dict
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>. ### Problem You are given a list of words. Construct an acronym that satisfies the following conditions: 1) is at least 5 characters 2) uses the first letter...
acronym_5o
acronym
[ { "content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.\n\n ### Problem\n\n\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\n1) is at least 5 charac...
[]
[]
{"acronym": "sound", "words": ["suite", "opener", "unnecessary", "nazis", "deleted"], "word_count": 5, "formed_acronym": "sound", "task_config": "acronym_5o", "task_source": "acronym"}
test
null
[ "<think>\nFirst, I have the list of words: ['suite', 'opener', 'unnecessary', 'nazis', 'deleted']. I need to construct an acronym that meets several criteria:\n\n1. It must be at least 5 characters long.\n2. It should use the first letter of at least 5 words in the list.\n3. Only the first letters of the chosen wor...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://10.32.37.28:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": {"chat_template_applied": true, "max_tokens": 16384, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8}, "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only", "n_responses": 4}
[ false, true, false, false ]
[ "sonid", "sound", "sonnd", "uncased" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 10592, "span_end": 10599, "original_span": "sonid"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 8220, "span_end": 8227, "original_span": "sound"}, {"extraction_type": "fina...
[{"is_correct": false, "error": "Constraint violations: not_valid_english_word, violates_character_position_constraint", "answer_block": "sonid", "final_answer": "sonid", "length": 5}, {"is_correct": true, "error": null, "answer_block": "sound", "final_answer": "sound", "length": 5}, {"is_correct": false, "error": "Con...
[ [ false ], [ true, true ], [ false, false ], [ false, false ] ]
[ [ "sonid" ], [ "sound", "sound" ], [ "(your answer)", "sonnd" ], [ "idea", "uncased" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 10592, "span_text": "sonid", "extraction_type": "internal", "span_start": 10592, "span_end": 10599, "original_span": "sonid"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 6015, "span_text": "sound", "extraction_type": "internal", "span_...
[[{"is_correct": false, "error": "Constraint violations: not_valid_english_word, violates_character_position_constraint", "answer_block": "sonid", "final_answer": "sonid", "length": 5}], [{"is_correct": true, "error": null, "answer_block": "sound", "final_answer": "sound", "length": 5}, {"is_correct": true, "error": nu...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.25, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, ...
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
sound
sound
5
[ "suite", "opener", "unnecessary", "nazis", "deleted" ]
null
null
61
2
2
<think> First, I have the list of words: ['suite', 'opener', 'unnecessary', 'nazis', 'deleted']. I need to construct an acronym that meets these criteria: 1. It must be at least 5 characters long. 2. It should use the first letter of at least 5 words in the list. 3. Only letters from a subset of the words should be u...
{ "response": "<think>\nFirst, I have the list of words: ['suite', 'opener', 'unnecessary', 'nazis', 'deleted'].\n\nI need to construct an acronym that meets these criteria:\n\n1. It must be at least 5 characters long.\n2. It should use the first letter of at least 5 words in the list.\n3. Only letters from a subset ...
[ "<think>\nFirst, I have the list of words: ['suite', 'opener', 'unnecessary', 'nazis', 'deleted'].\n\nI need to construct an acronym that meets these criteria:\n\n1. It must be at least 5 characters long.\n2. It should use the first letter of at least 5 words in the list.\n3. Only letters from a subset of the words...
[ false, false, false, false ]
[ "sonnd", "sonnd", "sonnd", "sonnd" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 6675, "span_end": 6682, "original_span": "sonnd"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 7474, "span_end": 7479, "original_span": "sonnd"}, {"extraction_type": "final"...
[{"is_correct": false, "error": "Constraint violations: not_valid_english_word, violates_character_position_constraint", "answer_block": "sonnd", "final_answer": "sonnd", "length": 5}, {"is_correct": false, "error": "Constraint violations: not_valid_english_word, violates_character_position_constraint", "answer_block":...
[ [ false, false ], [ false, false ], [ false, false ], [ false, false ] ]
[ [ "(your answer)", "sonnd" ], [ "(your answer)", "sonnd" ], [ "(your answer)", "sonnd" ], [ "(your answer)", "sonnd" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 5020, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 5020, "span_end": 5037, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 6675, "span_text": "sonnd", "extraction_type": "intern...
[[{"is_correct": false, "error": "Constraint violations: not_valid_english_word, invalid_length, violates_character_position_constraint", "answer_block": "(your answer)", "final_answer": "youranswer", "length": 10}, {"is_correct": false, "error": "Constraint violations: not_valid_english_word, violates_character_positi...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, 0, ...
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"media\", \"words\": [\"maps\", \"enable\", \"declaring\", \"infections\", \"autumn\(...TRUNCATED)
test
null
["<think>\nFirst, I have the list of words: ['maps', 'enable', 'declaring', 'infections', 'autumn'].(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "Mediate", "Idea", "meida", "medit" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_pos(...TRUNCATED)
[ [ false ], [ false, false, false ], [ false, false ], [ false, false ] ]
[ [ "Mediate" ], [ "(your answer)", "Idea", "Idea" ], [ "(your answer)", "meida" ], [ "...", "medit" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 9035, \"span_text\": \"Medi(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
media
media
5
[ "maps", "enable", "declaring", "infections", "autumn" ]
null
null
28
3
3
"<think>\nFirst, I have the list of words: ['maps', 'enable', 'declaring', 'infections', 'autumn'].\(...TRUNCATED)
{"response":"<think>\nFirst, I have the list of words: ['maps', 'enable', 'declaring', 'infections',(...TRUNCATED)
["<think>\nFirst, I have the list of words: ['maps', 'enable', 'declaring', 'infections', 'autumn'].(...TRUNCATED)
[ false, false, false, false ]
[ "medit", "medit", "medit", "medit" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, violates_chara(...TRUNCATED)
[ [ false, false ], [ false, false, false ], [ false, false, false ], [ false, false, false ] ]
[ [ "...", "medit" ], [ "...", "idea", "medit" ], [ "...", "idea", "medit" ], [ "...", "idea", "medit" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5717, \"span_text\": \"...\(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: 'no_acronym'\", \"answer_block\": \".(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"final\", \"words\": [\"forbidden\", \"interest\", \"none\", \"afford\", \"leaked\"](...TRUNCATED)
test
null
["<think>\nI need to create an acronym based on the given list of words. Let me write down the list:(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "finled", "Finale", "afelea", "finale" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED)
[ [ false, false, false ], [ false, false ], [ false, false, false ], [ false, false, false ] ]
[["idea","finled","finled"],["(your answer)","Finale"],["idea","idea","afelea"],["idea","(your answe(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2840, \"span_text\": \"idea(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
final
final
5
[ "forbidden", "interest", "none", "afford", "leaked" ]
null
null
32
2
2
"<think>\nFirst, I have the list of words: ['forbidden', 'interest', 'none', 'afford', 'leaked'].\n\(...TRUNCATED)
{"response":"<think>\nFirst, I have the list of words: ['forbidden', 'interest', 'none', 'afford', '(...TRUNCATED)
["<think>\nFirst, I have the list of words: ['forbidden', 'interest', 'none', 'afford', 'leaked'].\n(...TRUNCATED)
[ false, false, false, false ]
[ "afelea", "afelea", "afelea", "afelea" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED)
[[false,false,false],[false,false,false,false],[false,false,false,false,false],[false,false,false,fa(...TRUNCATED)
[["idea","idea","afelea"],["idea","idea","afelea","afelea"],["idea","idea","afelea","afelea","afelea(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6024, \"span_text\": \"idea(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"model\", \"words\": [\"many\", \"olivia\", \"danny\", \"eleanor\", \"loans\"], \"wo(...TRUNCATED)
test
null
["<think>\nFirst, I have the list of words: ['many', 'olivia', 'danny', 'eleanor', 'loans']. I need (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "maneno", null, "moalee", "meldal" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED)
[ [ false, false, false ], [], [ false, false, false, false ], [ false, false ] ]
[ [ "...", "maneno", "maneno" ], [], [ "(your answer)", "(your answer)", "iota", "moalee" ], [ "idea", "meldal" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6483, \"span_text\": \"...\(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: 'no_acronym'\", \"answer_block\": \".(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
model
model
5
[ "many", "olivia", "danny", "eleanor", "loans" ]
null
null
68
3
3
"<think>\nFirst, I have the list of words: ['many', 'olivia', 'danny', 'eleanor', 'loans'].\n\nI nee(...TRUNCATED)
{"response":"<think>\nFirst, I have the list of words: ['many', 'olivia', 'danny', 'eleanor', 'loans(...TRUNCATED)
["<think>\nFirst, I have the list of words: ['many', 'olivia', 'danny', 'eleanor', 'loans'].\n\nI ne(...TRUNCATED)
[ false, false, false, false ]
[ "meldal", "medal", "medal", "medal" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED)
[ [ false, false ], [ false, false, false ], [ false, false, false ], [ false, false, false ] ]
[ [ "idea", "meldal" ], [ "idea", "medal", "medal" ], [ "idea", "medal", "medal" ], [ "idea", "medal", "medal" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5294, \"span_text\": \"idea(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"daily\", \"words\": [\"decent\", \"account\", \"illusion\", \"leaving\", \"yields\"(...TRUNCATED)
test
null
["<think>\nI need to construct an acronym based on the given list of words, but with some specific r(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ null, "idea", "Account", "idea" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false, false, false ], [ false, false, false, false ], [ false, false, false ] ]
[ [], [ "idea", "(your answer)", "idea" ], [ "idea", "Account", "Account", "Account" ], [ "idea", "idea", "idea" ] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6737, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_characte(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
daily
daily
5
[ "decent", "account", "illusion", "leaving", "yields" ]
null
null
84
2
2
"<think>\nFirst, I have the list of words: ['decent', 'account', 'illusion', 'leaving', 'yields']. I(...TRUNCATED)
{"response":"<think>\nFirst, I have the list of words: ['decent', 'account', 'illusion', 'leaving', (...TRUNCATED)
["<think>\nFirst, I have the list of words: ['decent', 'account', 'illusion', 'leaving', 'yields']. (...TRUNCATED)
[ false, false, false, false ]
[ "Account", "Account", "Account", "Account" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_pos(...TRUNCATED)
[[false,false,false,false],[false,false,false,false],[false,false,false,false],[false,false,false,fa(...TRUNCATED)
[["idea","Account","Account","Account"],["idea","Account","Account","Account"],["idea","Account","Ac(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5314, \"span_text\": \"idea(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"until\", \"words\": [\"underground\", \"nominee\", \"dylan\", \"taxi\", \"instant\"(...TRUNCATED)
test
null
["<think>\nFirst, I need to construct an acronym that meets all the criteria. Let me write them down(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ null, null, "(your answer)", "UNDOTI" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [ false, false, false ] ]
[ [], [], [ "(your answer)" ], [ "(your answer)", "(your answer)", "UNDOTI" ] ]
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 11573, \"span_text\(...TRUNCATED)
"[[], [], [{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, inval(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
until
until
6
[ "underground", "nominee", "dylan", "taxi", "instant", "lead" ]
null
null
100
1
1
"<think>\nFirst, I need to understand the requirements for constructing an acronym.\n\n1) The acrony(...TRUNCATED)
{"response":"<think>\nFirst, I need to understand the requirements for constructing an acronym.\n\n1(...TRUNCATED)
["<think>\nFirst, I need to understand the requirements for constructing an acronym.\n\n1) The acron(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"lives\", \"words\": [\"literacy\", \"interact\", \"valve\", \"elect\", \"separately(...TRUNCATED)
test
null
["<think>\nI need to create an acronym based on the given list of words, but there are some specific(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "idema", "idea", "None of the above", "idea" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, violates_chara(...TRUNCATED)
[ [ false, false, false, false ], [ false, false, false ], [ false, false, false, false ], [ false, false, false ] ]
[["idea","(your answer)","idema","idema"],["(your answer)","(your answer)","idea"],["(your answer)",(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5296, \"span_text\": \"idea(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
lives
lives
5
[ "literacy", "interact", "valve", "elect", "separately" ]
null
null
63
2
2
"<think>\nFirst, I have the list of words: ['literacy', 'interact', 'valve', 'elect', 'separately'].(...TRUNCATED)
{"response":"<think>\nFirst, I have the list of words: ['literacy', 'interact', 'valve', 'elect', 's(...TRUNCATED)
["<think>\nFirst, I have the list of words: ['literacy', 'interact', 'valve', 'elect', 'separately'](...TRUNCATED)
[ false, false, false, false ]
[ "None of the above", "None of the above", "None of the above", "None of the above" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED)
[[false,false,false,false],[false,false,false,false],[false,false,false,false],[false,false,false,fa(...TRUNCATED)
[["(your answer)","None of the above","(your answer)","None of the above"],["(your answer)","None of(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 10287, \"span_text\": \"(yo(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_lengt(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"takes\", \"words\": [\"tragedy\", \"absent\", \"knows\", \"exile\", \"striking\"], (...TRUNCATED)
test
null
["<think>\nFirst, I have the list of words: ['tragedy', 'absent', 'knows', 'exile', 'striking'].\n\n(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "idea", "tanes", "(your answer)", "(your answer)" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_pos(...TRUNCATED)
[ [ false, false, false ], [ false, false, false ], [ false, false ], [ false ] ]
[["idea","(your answer)","idea"],["(your answer)","tanes","tanes"],["(your answer)","(your answer)"](...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5186, \"span_text\": \"idea(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_po(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
takes
takes
5
[ "tragedy", "absent", "knows", "exile", "striking" ]
null
null
53
3
3
"<think>\nI need to create an acronym based on the given list of words. Let me look at the requireme(...TRUNCATED)
{"response":"<think>\nI need to create an acronym based on the given list of words. Let me look at t(...TRUNCATED)
["<think>\nI need to create an acronym based on the given list of words. Let me look at the requirem(...TRUNCATED)
[ false, false, false, false ]
[ "(your answer)", "(your answer)", "(your answer)", "(your answer)" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED)
[ [ false ], [ false ], [ false ], [ false ] ]
[ [ "(your answer)" ], [ "(your answer)" ], [ "(your answer)" ], [ "(your answer)" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8174, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_lengt(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"terms\", \"words\": [\"trees\", \"existence\", \"rushed\", \"measures\", \"substant(...TRUNCATED)
test
null
["<think>\nI need to construct an acronym that meets several criteria. Let me break it down.\n\n1. T(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, true, false ]
[ "termes", null, "terms", "texas" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Constraint violations: invalid_length, violates_character_pos(...TRUNCATED)
[ [ false, false, false, false ], [], [ true ], [ false, false, false, false, false, false ] ]
[["(your answer)","termes","(your answer)","termes"],[],["terms"],["...","texas","...","texas","texa(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3582, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_lengt(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
terms
terms
5
[ "trees", "existence", "rushed", "measures", "substantial" ]
null
null
77
2
2
"<think>\nFirst, I need to construct an acronym based on the given criteria. Let me go through them (...TRUNCATED)
{"response":"<think>\nFirst, I need to construct an acronym based on the given criteria. Let me go t(...TRUNCATED)
["<think>\nFirst, I need to construct an acronym based on the given criteria. Let me go through them(...TRUNCATED)
[ true, true, true, true ]
[ "terms", "terms", "terms", "terms" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"terms\", \"final_answer\": \"terms\", (...TRUNCATED)
[ [ true ], [ true ], [ true ], [ true ] ]
[ [ "terms" ], [ "terms" ], [ "terms" ], [ "terms" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8805, \"span_text\": \"term(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"terms\", \"final_answer\": \"terms\",(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
acronym_5o
acronym
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"acronym\": \"world\", \"words\": [\"wizard\", \"options\", \"rubber\", \"likewise\", \"dancers\"(...TRUNCATED)
test
null
["<think>\nFirst, I have the list of words: ['wizard', 'options', 'rubber', 'likewise', 'dancers'].\(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ null, null, "word", "weird" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false, false, false, false ], [ false ] ]
[ [], [], [ "(your answer)", "word", "word", "word" ], [ "weird" ] ]
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4308, \"span_text\"(...TRUNCATED)
"[[], [], [{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, inval(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
world
world
5
[ "wizard", "options", "rubber", "likewise", "dancers" ]
null
null
4
1
1
"<think>\nFirst, I have the list of words: ['wizard', 'options', 'rubber', 'likewise', 'dancers'].\n(...TRUNCATED)
{"response":"<think>\nFirst, I have the list of words: ['wizard', 'options', 'rubber', 'likewise', '(...TRUNCATED)
["<think>\nFirst, I have the list of words: ['wizard', 'options', 'rubber', 'likewise', 'dancers'].\(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
3