| { |
| "schema_version": "0.2.2", |
| "evaluation_id": "mmlu_pro_chat/RedHatAI/MiniMax-M2.5-NVFP4/1777381372.569359", |
| "evaluation_timestamp": "1776209745", |
| "retrieved_timestamp": "1777381372.569359", |
| "source_metadata": { |
| "source_name": "lm-evaluation-harness", |
| "source_type": "evaluation_run", |
| "source_organization_name": "RedHatAI", |
| "evaluator_relationship": "third_party" |
| }, |
| "eval_library": { |
| "name": "lm_eval", |
| "version": "0.4.12.dev0" |
| }, |
| "model_info": { |
| "name": "RedHatAI/MiniMax-M2.5-NVFP4", |
| "id": "RedHatAI/MiniMax-M2.5-NVFP4", |
| "developer": "RedHatAI", |
| "additional_details": { |
| "model_args": "{'model': 'RedHatAI/MiniMax-M2.5-NVFP4', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}", |
| "seed": "1234", |
| "num_seeds_merged": "3" |
| } |
| }, |
| "evaluation_results": [ |
| { |
| "evaluation_name": "mmlu_pro_chat_biology/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.903300790330079, |
| "details": { |
| "seed_scores": "[0.9121338912133892, 0.9037656903765691, 0.8940027894002789]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.005239157447505677, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_business/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8588931136459653, |
| "details": { |
| "seed_scores": "[0.8605830164765526, 0.8504435994930292, 0.8656527249683144]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.004471062629597958, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_chemistry/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8674911660777385, |
| "details": { |
| "seed_scores": "[0.8666077738515902, 0.8683745583038869, 0.8674911660777385]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0005100267395667788, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_computer_science/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8569105691056911, |
| "details": { |
| "seed_scores": "[0.875609756097561, 0.8512195121951219, 0.8439024390243902]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.009585224489879356, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_economics/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8404423380726699, |
| "details": { |
| "seed_scores": "[0.8376777251184834, 0.840047393364929, 0.8436018957345972]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.001721524069328884, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_engineering/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7220502235982112, |
| "details": { |
| "seed_scores": "[0.7409700722394221, 0.6996904024767802, 0.7254901960784313]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.012039903680770573, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_health/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7766911165444174, |
| "details": { |
| "seed_scores": "[0.7701711491442543, 0.78239608801956, 0.7775061124694377]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0035524848765612657, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_history/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.6500437445319335, |
| "details": { |
| "seed_scores": "[0.6272965879265092, 0.6509186351706037, 0.6719160104986877]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.01288794388683834, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_law/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.55858310626703, |
| "details": { |
| "seed_scores": "[0.5640326975476839, 0.5404178019981835, 0.5712988192552225]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.00932171015340034, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_math/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.9338761411300271, |
| "details": { |
| "seed_scores": "[0.9341228719467062, 0.9356032568467801, 0.9319022945965951]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0010754746961610265, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_other/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7525252525252526, |
| "details": { |
| "seed_scores": "[0.762987012987013, 0.7435064935064936, 0.7510822510822511]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.005669636957251685, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_philosophy/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.6893787575150301, |
| "details": { |
| "seed_scores": "[0.6833667334669339, 0.685370741482966, 0.6993987975951904]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0050433095759991695, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_physics/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8763151141904029, |
| "details": { |
| "seed_scores": "[0.8752886836027713, 0.876058506543495, 0.8775981524249422]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0006789200182357032, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat_psychology/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.789891395154553, |
| "details": { |
| "seed_scores": "[0.7869674185463659, 0.7907268170426065, 0.7919799498746867]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0015060782270108586, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 40.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "presence_penalty": "1.5", |
| "repetition_penalty": "1.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "mmlu_pro_chat/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "other" |
| }, |
| "evaluation_timestamp": "1776226127", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8008089539007092, |
| "details": { |
| "seed_scores": "[0.8029421542553191, 0.7964594414893617, 0.8030252659574468]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.002174888545121904, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| } |
| } |
| ] |
| } |
