{ "2025-11-03T14-26-12+01-00_hle_Y5Ra7r6MVZ6AqaggbXGZnZ.eval": { "eval_id": "96nrTiYaUKyqA4L2KzJftb", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "Y5Ra7r6MVZ6AqaggbXGZnZ", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:featherless-ai", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:29:06+01:00", "primary_metric": { "name": "accuracy", "value": 0.36363636363636365, "params": {} } }, "2025-11-03T14-26-12+01-00_hle_cvB8VVcXWR4Dzb7fVRi8mV.eval": { "eval_id": "fQSrawbJLDbBKKBTDVHjUK", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "cvB8VVcXWR4Dzb7fVRi8mV", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:sambanova", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:28:46+01:00", "primary_metric": { "name": "accuracy", "value": 0.2727272727272727, "params": {} } }, "2025-11-03T14-26-12+01-00_hle_F36GRHf949FGCqCTrePjQB.eval": { "eval_id": "ZwCzZjY7VJ9EhFZvQFMXmz", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "F36GRHf949FGCqCTrePjQB", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:novita", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:27:08+01:00", "primary_metric": { "name": "accuracy", "value": 0.36363636363636365, "params": {} } }, "2025-11-03T14-26-12+01-00_hle_fFud4d4o8o5S5W5aXsovDc.eval": { "eval_id": "Z9sjmsbnAZvuFELToKGP8j", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "fFud4d4o8o5S5W5aXsovDc", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:nebius", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:27:04+01:00", "primary_metric": { "name": "accuracy", "value": 0.09090909090909091, "params": {} } }, "2025-11-03T14-26-12+01-00_hle_oSRQLhvnxDmCTvWRyMmEci.eval": { "eval_id": "n7GX2ATrYULuAGG6jar9hG", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "oSRQLhvnxDmCTvWRyMmEci", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:cerebras", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:27:03+01:00", "primary_metric": { "name": "accuracy", "value": 0.5454545454545454, "params": {} } }, "2025-11-03T14-26-12+01-00_hle_nCpdHBTayRK3w284wBFxxB.eval": { "eval_id": "5WLZBSKJPm6ib36YUGNmAh", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "nCpdHBTayRK3w284wBFxxB", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:scaleway", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:26:55+01:00", "primary_metric": { "name": "accuracy", "value": 0.18181818181818182, "params": {} } }, "2025-11-03T14-26-12+01-00_hle_XNqPjB6KhFEPyuALx8fDdb.eval": { "eval_id": "UKdb2Q6CPAYUD5jkgkAk3n", "run_id": "j7teXye7wX6EmW8Xsg6iBx", "task": "hle", "task_id": "XNqPjB6KhFEPyuALx8fDdb", "task_version": 0, "version": 2, "status": "success", "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct:fireworks-ai", "started_at": "2025-11-03T14:26:12+01:00", "completed_at": "2025-11-03T14:26:52+01:00", "primary_metric": { "name": "accuracy", "value": 0.09090909090909091, "params": {} } } }