{ "eval_version": "sn-loop-eval-v1", "model": "sensenova-loop-nvfp4", "base_url": "http://127.0.0.1:30080/v1", "started": "2026-10-30T17:17:37-0700", "enable_thinking": false, "sampling": { "temperature": 0.0, "top_p": 1.0, "seed": 0, "max_tokens": { "ifeval": 1024, "gsm8k": 1024, "mmlu_pro": 1024, "humaneval": 1024, "tools": 512, "vqa": 64 } }, "concurrency": 16, "limit": null, "host": "tux", "data_sha256": { "ifeval": "3e9e9e7bd42ef54862f0c71c9a4e6f0b17a9c259f8f4b2b4e5fbcad917228118", "gsm8k": "5bb91d328c1ffc424d6679fe8edb36ed08152e4c75e75b343303e15cacc2da49", "mmlu_pro": "e9d8d5717def43a0b995710ab093a13de48b4cfb4db19cd7c66affacfb492ea7", "humaneval": "1e775e30085b890c19c48a583bfabb8f5f54598b5bf54796839b92e5bafdab9f", "tools": "037b2e288f4f063e8a2d994799b4a51e4d97740b1cf62da75844243749dbb08a", "vqa": "7d47303ecdf3386d04a852ab8b7e8be8d34137a1c4d10143331cc7175ce80d9d" }, "tasks": { "gsm8k": { "n": 80, "correct": 77, "accuracy": 0.9625, "wilson95": [ 0.8954527983617241, 0.9871654311799435 ], "n_errors": 0, "n_truncated": 1, "mean_completion_tokens": 190.3875, "sum_completion_tokens": 15231, "wall_s": 94.6 }, "humaneval": { "n": 40, "correct": 32, "accuracy": 0.8, "wilson95": [ 0.6524269352437855, 0.8950001032811363 ], "n_errors": 0, "n_truncated": 0, "mean_completion_tokens": 191.3, "sum_completion_tokens": 7652, "wall_s": 46.1 }, "tools": { "n": 20, "correct": 18, "accuracy": 0.9, "wilson95": [ 0.6989663528135878, 0.9721335190383086 ], "n_errors": 0, "n_truncated": 0, "mean_completion_tokens": 60.2, "sum_completion_tokens": 1204, "names_correct": 0.9, "parse_source_counts": { "server": 15, "none": 5 }, "format_well_formed": 1.0, "raw_tool_call_tags_in_content": 0, "by_category": { "irrelevance": "3/3", "multiple": "5/6", "parallel": "3/3", "simple": "7/8" }, "wall_s": 16.6 } }, "server_models": { "object": "list", "data": [ { "id": "sensenova-loop-nvfp4", "object": "model", "created": 1793405857, "owned_by": "sglang", "root": "sensenova-loop-nvfp4", "parent": null, "max_model_len": 32768 } ] }, "wall_s": 157.4 }