| { | |
| "2025-11-20T15-36-59+01-00_long-horizon-execution-8192_Gm6T2GREQg6indZWYr7qUY.eval": { | |
| "eval_id": "NA7cVCboUagosQMLCMyfpQ", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:8192", | |
| "task_id": "Gm6T2GREQg6indZWYr7qUY", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:38:46+01:00", | |
| "completed_at": "2025-11-20T15:44:01+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.01, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-36-58+01-00_long-horizon-execution-4096_W3QMv8KVUf2BLSRZArAxzd.eval": { | |
| "eval_id": "jJPdv4eRojLxynfw2MAedo", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:4096", | |
| "task_id": "W3QMv8KVUf2BLSRZArAxzd", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:37:40+01:00", | |
| "completed_at": "2025-11-20T15:42:05+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.84, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-36-58+01-00_long-horizon-execution-65536_GmtEQzBe5eEKggR8HdoNoV.eval": { | |
| "eval_id": "VhLNjTUfqn7yKq944iKk22", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:65536", | |
| "task_id": "GmtEQzBe5eEKggR8HdoNoV", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:37:50+01:00", | |
| "completed_at": "2025-11-20T15:40:03+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-36-58+01-00_long-horizon-execution-2048_Uvr76zF8hkt4PgnsUPDWDS.eval": { | |
| "eval_id": "UjKsVmVMSAm66eNny39LSK", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:2048", | |
| "task_id": "Uvr76zF8hkt4PgnsUPDWDS", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:36:59+01:00", | |
| "completed_at": "2025-11-20T15:39:10+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 1.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-36-58+01-00_long-horizon-execution-32768_FZ9Z2AZfBoMdRpzJ3Rt4Sx.eval": { | |
| "eval_id": "ad6DnHZEH9zkVdEAgJhwCP", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:32768", | |
| "task_id": "FZ9Z2AZfBoMdRpzJ3Rt4Sx", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:36:59+01:00", | |
| "completed_at": "2025-11-20T15:38:46+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-36-58+01-00_long-horizon-execution-16384_mwMLFEBj8eYRiiYPvyD7Xd.eval": { | |
| "eval_id": "QAVERTysNLU62kRvZQoAk5", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:16384", | |
| "task_id": "mwMLFEBj8eYRiiYPvyD7Xd", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:36:59+01:00", | |
| "completed_at": "2025-11-20T15:37:50+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-36-58+01-00_long-horizon-execution-1024_Q8FPP67tZkwjmyx7MrkPdK.eval": { | |
| "eval_id": "VTJ4tkhiXzyqpfyvDkqQbu", | |
| "run_id": "bpaANsnXqDLDYGsQaQY7As", | |
| "task": "long_horizon_execution:1024", | |
| "task_id": "Q8FPP67tZkwjmyx7MrkPdK", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:36:59+01:00", | |
| "completed_at": "2025-11-20T15:37:40+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 1.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-8192_QZ55FqjvLpVzDPfU4CgkdJ.eval": { | |
| "eval_id": "XHSj88vvSCBdgLtCbsSZgQ", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:8192", | |
| "task_id": "QZ55FqjvLpVzDPfU4CgkdJ", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:05+01:00", | |
| "completed_at": "2025-11-20T15:33:19+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-4096_6KngaNoJcesYZ3n4wHJtgr.eval": { | |
| "eval_id": "eghpYmgJXjVQzyUrJeqNrD", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:4096", | |
| "task_id": "6KngaNoJcesYZ3n4wHJtgr", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:03+01:00", | |
| "completed_at": "2025-11-20T15:33:19+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-16384_MSnnENqGY9aXtE549VWfYY.eval": { | |
| "eval_id": "Cbm4Ms6j4DDm82JW6JhjoC", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:16384", | |
| "task_id": "MSnnENqGY9aXtE549VWfYY", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:02+01:00", | |
| "completed_at": "2025-11-20T15:33:10+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-65536_MKNbbyxFi2SboYmzcZJg7i.eval": { | |
| "eval_id": "2HyufGWpesgASQDYAQWibj", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:65536", | |
| "task_id": "MKNbbyxFi2SboYmzcZJg7i", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:03+01:00", | |
| "completed_at": "2025-11-20T15:33:10+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-1024_hFHo95vmjgTchZGoSC4pPM.eval": { | |
| "eval_id": "RGPNvdwwBVqBcb4gwPKdpN", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:1024", | |
| "task_id": "hFHo95vmjgTchZGoSC4pPM", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:02+01:00", | |
| "completed_at": "2025-11-20T15:33:05+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 1.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-32768_Vh2nnbhMtb7hpmk8zMRe7R.eval": { | |
| "eval_id": "7MNDPdZ7F6phteuzwWGHbq", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:32768", | |
| "task_id": "Vh2nnbhMtb7hpmk8zMRe7R", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:02+01:00", | |
| "completed_at": "2025-11-20T15:33:03+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.0, | |
| "params": {} | |
| } | |
| }, | |
| "2025-11-20T15-33-02+01-00_long-horizon-execution-2048_g4ytLJepzwxhnKAFsCRkcZ.eval": { | |
| "eval_id": "d5GJrLaBTUyvhTWfuCn6Pb", | |
| "run_id": "GFRyNerPFXSvUcW5wjmccn", | |
| "task": "long_horizon_execution:2048", | |
| "task_id": "g4ytLJepzwxhnKAFsCRkcZ", | |
| "task_version": 0, | |
| "version": 2, | |
| "status": "success", | |
| "model": "hf-inference-providers/openai/gpt-oss-20b", | |
| "started_at": "2025-11-20T15:33:02+01:00", | |
| "completed_at": "2025-11-20T15:33:03+01:00", | |
| "primary_metric": { | |
| "name": "accuracy", | |
| "value": 0.5, | |
| "params": {} | |
| } | |
| } | |
| } |