SaylorTwift/inspect-bundle
0
1{2 "2025-11-03T14-26-12+01-00_hle_Y5Ra7r6MVZ6AqaggbXGZnZ.eval": {3 "eval_id": "96nrTiYaUKyqA4L2KzJftb",4 "run_id": "j7teXye7wX6EmW8Xsg6iBx",5 "task": "hle",6 "task_id": "Y5Ra7r6MVZ6AqaggbXGZnZ",7 "task_version": 0,8 "version": 2,9 "status": "success",10 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:featherless-ai",11 "started_at": "2025-11-03T14:26:12+01:00",12 "completed_at": "2025-11-03T14:29:06+01:00",13 "primary_metric": {14 "name": "accuracy",15 "value": 0.36363636363636365,16 "params": {}17 }18 },19 "2025-11-03T14-26-12+01-00_hle_cvB8VVcXWR4Dzb7fVRi8mV.eval": {20 "eval_id": "fQSrawbJLDbBKKBTDVHjUK",21 "run_id": "j7teXye7wX6EmW8Xsg6iBx",22 "task": "hle",23 "task_id": "cvB8VVcXWR4Dzb7fVRi8mV",24 "task_version": 0,25 "version": 2,26 "status": "success",27 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:sambanova",28 "started_at": "2025-11-03T14:26:12+01:00",29 "completed_at": "2025-11-03T14:28:46+01:00",30 "primary_metric": {31 "name": "accuracy",32 "value": 0.2727272727272727,33 "params": {}34 }35 },36 "2025-11-03T14-26-12+01-00_hle_F36GRHf949FGCqCTrePjQB.eval": {37 "eval_id": "ZwCzZjY7VJ9EhFZvQFMXmz",38 "run_id": "j7teXye7wX6EmW8Xsg6iBx",39 "task": "hle",40 "task_id": "F36GRHf949FGCqCTrePjQB",41 "task_version": 0,42 "version": 2,43 "status": "success",44 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:novita",45 "started_at": "2025-11-03T14:26:12+01:00",46 "completed_at": "2025-11-03T14:27:08+01:00",47 "primary_metric": {48 "name": "accuracy",49 "value": 0.36363636363636365,50 "params": {}51 }52 },53 "2025-11-03T14-26-12+01-00_hle_fFud4d4o8o5S5W5aXsovDc.eval": {54 "eval_id": "Z9sjmsbnAZvuFELToKGP8j",55 "run_id": "j7teXye7wX6EmW8Xsg6iBx",56 "task": "hle",57 "task_id": "fFud4d4o8o5S5W5aXsovDc",58 "task_version": 0,59 "version": 2,60 "status": "success",61 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:nebius",62 "started_at": "2025-11-03T14:26:12+01:00",63 "completed_at": "2025-11-03T14:27:04+01:00",64 "primary_metric": {65 "name": "accuracy",66 "value": 0.09090909090909091,67 "params": {}68 }69 },70 "2025-11-03T14-26-12+01-00_hle_oSRQLhvnxDmCTvWRyMmEci.eval": {71 "eval_id": "n7GX2ATrYULuAGG6jar9hG",72 "run_id": "j7teXye7wX6EmW8Xsg6iBx",73 "task": "hle",74 "task_id": "oSRQLhvnxDmCTvWRyMmEci",75 "task_version": 0,76 "version": 2,77 "status": "success",78 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:cerebras",79 "started_at": "2025-11-03T14:26:12+01:00",80 "completed_at": "2025-11-03T14:27:03+01:00",81 "primary_metric": {82 "name": "accuracy",83 "value": 0.5454545454545454,84 "params": {}85 }86 },87 "2025-11-03T14-26-12+01-00_hle_nCpdHBTayRK3w284wBFxxB.eval": {88 "eval_id": "5WLZBSKJPm6ib36YUGNmAh",89 "run_id": "j7teXye7wX6EmW8Xsg6iBx",90 "task": "hle",91 "task_id": "nCpdHBTayRK3w284wBFxxB",92 "task_version": 0,93 "version": 2,94 "status": "success",95 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:scaleway",96 "started_at": "2025-11-03T14:26:12+01:00",97 "completed_at": "2025-11-03T14:26:55+01:00",98 "primary_metric": {99 "name": "accuracy",100 "value": 0.18181818181818182,101 "params": {}102 }103 },104 "2025-11-03T14-26-12+01-00_hle_XNqPjB6KhFEPyuALx8fDdb.eval": {105 "eval_id": "UKdb2Q6CPAYUD5jkgkAk3n",106 "run_id": "j7teXye7wX6EmW8Xsg6iBx",107 "task": "hle",108 "task_id": "XNqPjB6KhFEPyuALx8fDdb",109 "task_version": 0,110 "version": 2,111 "status": "success",112 "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:fireworks-ai",113 "started_at": "2025-11-03T14:26:12+01:00",114 "completed_at": "2025-11-03T14:26:52+01:00",115 "primary_metric": {116 "name": "accuracy",117 "value": 0.09090909090909091,118 "params": {}119 }120 }121}