{ "accepted_benchmark_count": 7, "accepted_benchmarks": [ "aime2025", "arenahardwriting", "bfcl", "gpqamain", "gsm8k", "healthbench", "humaneval" ], "accepted_model_count": 4, "accepted_models": { "HuggingFaceTB_SmolLM3-3B-Base": "SmolLM3-3B-Base", "Qwen_Qwen3-1.7B-Base": "Qwen3-1.7B-Base", "Qwen_Qwen3-4B-Base": "Qwen3-4B-Base", "google_gemma-3-4b-pt": "Gemma-3-4B-PT" }, "cell_counts": { "aime2025": [ 47, 48, 48, 48 ], "arenahardwriting": [ 47, 48, 50, 48 ], "bfcl": [ 47, 48, 48, 48 ], "gpqamain": [ 46, 49, 47, 49 ], "gsm8k": [ 47, 47, 49, 48 ], "healthbench": [ 47, 48, 48, 48 ], "humaneval": [ 47, 47, 48, 48 ] }, "duplicate_job_pairs": 25, "excluded_auxiliary_data": { "counted_as_task_root": false, "directory_count": 1, "file_count": 2397, "present": true, "top_level_path": "viewer_data" }, "excluded_dirs_count": 0, "inventory": { "all_entries_digest": "045ae5c714aa605b4295e345970cdf9a330600f709ef18508e8bef5eb3eec13d", "dir_count": 14117, "dir_entries_digest": "d480b9917811f32cfe7e055a029f475bfb2fa0c1cb02d0d08a7de0e200714132", "file_count": 97209, "file_entries_digest": "320253d2791e878f6539c58365ddc9ac93baffb53a5c78244910ef153f067ca4", "page_count": 112, "rejected_siblings_count": 85883, "rejected_siblings_digest": "116dc22723f1cc13bf71461ff83dd03479c74a2740957787e6ca642a59628eea", "total_entries": 111326 }, "matrix": [ { "benchmark": "aime2025", "count": 47, "model": "Qwen3-1.7B-Base" }, { "benchmark": "aime2025", "count": 48, "model": "Qwen3-4B-Base" }, { "benchmark": "aime2025", "count": 48, "model": "SmolLM3-3B-Base" }, { "benchmark": "aime2025", "count": 48, "model": "Gemma-3-4B-PT" }, { "benchmark": "arenahardwriting", "count": 47, "model": "Qwen3-1.7B-Base" }, { "benchmark": "arenahardwriting", "count": 48, "model": "Qwen3-4B-Base" }, { "benchmark": "arenahardwriting", "count": 50, "model": "SmolLM3-3B-Base" }, { "benchmark": "arenahardwriting", "count": 48, "model": "Gemma-3-4B-PT" }, { "benchmark": "bfcl", "count": 47, "model": "Qwen3-1.7B-Base" }, { "benchmark": "bfcl", "count": 48, "model": "Qwen3-4B-Base" }, { "benchmark": "bfcl", "count": 48, "model": "SmolLM3-3B-Base" }, { "benchmark": "bfcl", "count": 48, "model": "Gemma-3-4B-PT" }, { "benchmark": "gpqamain", "count": 46, "model": "Qwen3-1.7B-Base" }, { "benchmark": "gpqamain", "count": 49, "model": "Qwen3-4B-Base" }, { "benchmark": "gpqamain", "count": 47, "model": "SmolLM3-3B-Base" }, { "benchmark": "gpqamain", "count": 49, "model": "Gemma-3-4B-PT" }, { "benchmark": "gsm8k", "count": 47, "model": "Qwen3-1.7B-Base" }, { "benchmark": "gsm8k", "count": 47, "model": "Qwen3-4B-Base" }, { "benchmark": "gsm8k", "count": 49, "model": "SmolLM3-3B-Base" }, { "benchmark": "gsm8k", "count": 48, "model": "Gemma-3-4B-PT" }, { "benchmark": "healthbench", "count": 47, "model": "Qwen3-1.7B-Base" }, { "benchmark": "healthbench", "count": 48, "model": "Qwen3-4B-Base" }, { "benchmark": "healthbench", "count": 48, "model": "SmolLM3-3B-Base" }, { "benchmark": "healthbench", "count": 48, "model": "Gemma-3-4B-PT" }, { "benchmark": "humaneval", "count": 47, "model": "Qwen3-1.7B-Base" }, { "benchmark": "humaneval", "count": 47, "model": "Qwen3-4B-Base" }, { "benchmark": "humaneval", "count": 48, "model": "SmolLM3-3B-Base" }, { "benchmark": "humaneval", "count": 48, "model": "Gemma-3-4B-PT" } ], "missing_root_cell_pairs": 3, "protocol": { "commit_sh_analysis": { "current_benchmarks_in_arrays": [ "healthbench" ], "current_models_in_arrays": [ "Qwen/Qwen3-4B-Base" ], "gpu_counts_found": [ 8 ], "has_metr_branch": true, "htcondor_branch": { "active_jobs": 8, "gpu_spec": "default (single_task.sub num_gpus=1)", "one_hour_jobs": 1, "ten_hour_jobs": 7 }, "htcondor_mpi_is_branch": { "active_jobs": 1, "gpus": 8, "hours": 100, "note": "Active 100-hour, eight-GPU METR command" }, "num_hours_values": [ 1, 10, 100 ], "scheduler_dependent": true }, "cuda_device_requirement": "TARGET.CUDADeviceName == \"NVIDIA H100 80GB HBM3\"", "evaluation_dir_count": 7, "evaluation_dirs_present": [ "src/eval/tasks/aime2025", "src/eval/tasks/arenahardwriting", "src/eval/tasks/bfcl", "src/eval/tasks/gpqamain", "src/eval/tasks/gsm8k", "src/eval/tasks/healthbench", "src/eval/tasks/humaneval" ], "limitation_five_minute_grace": true, "limitation_multi_gpu_extension": true, "num_gpus_default": 1, "receives_num_hours": true, "request_gpus_binding": "request_gpus = $(num_gpus)", "solve_timeout_formula": "NUM_HOURS * 60 + 5", "source_references": { "commit_sh_analysis.current_benchmarks_in_arrays": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "3c43144e1186a160f450e747b95861fea6d16747", "lines": [ 18 ], "path": "src/commit_utils/commit.sh", "raw_sha256": "663ecb37cc4e6a16dcfcf8135bdbadf325f0b067192fe7a71d2231ba37eaae8e" }, "commit_sh_analysis.current_models_in_arrays": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "3c43144e1186a160f450e747b95861fea6d16747", "lines": [ 6 ], "path": "src/commit_utils/commit.sh", "raw_sha256": "663ecb37cc4e6a16dcfcf8135bdbadf325f0b067192fe7a71d2231ba37eaae8e" }, "commit_sh_analysis.htcondor_branch": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "3c43144e1186a160f450e747b95861fea6d16747", "lines": [ 83, 84, 85, 86, 87, 88, 89, 90 ], "path": "src/commit_utils/commit.sh", "raw_sha256": "663ecb37cc4e6a16dcfcf8135bdbadf325f0b067192fe7a71d2231ba37eaae8e" }, "commit_sh_analysis.htcondor_mpi_is_branch": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "3c43144e1186a160f450e747b95861fea6d16747", "lines": [ 48 ], "path": "src/commit_utils/commit.sh", "raw_sha256": "663ecb37cc4e6a16dcfcf8135bdbadf325f0b067192fe7a71d2231ba37eaae8e" }, "cuda_device_requirement": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "ea7f8790b97301dcdb6f3c104c5555d7ddf4e06a", "lines": [ 11 ], "path": "src/commit_utils/single_task.sub", "raw_sha256": "f8ee12da42fdebfc3b4293a22ea8b232c1f8f52cb2f52b103c9f138f0ddc013a" }, "evaluation_dirs_present": { "kind": "git-tree-entries", "paths": [ "src/eval/tasks/aime2025", "src/eval/tasks/arenahardwriting", "src/eval/tasks/bfcl", "src/eval/tasks/gpqamain", "src/eval/tasks/gsm8k", "src/eval/tasks/healthbench", "src/eval/tasks/humaneval" ] }, "num_gpus_default": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "ea7f8790b97301dcdb6f3c104c5555d7ddf4e06a", "lines": [ 2 ], "path": "src/commit_utils/single_task.sub", "raw_sha256": "f8ee12da42fdebfc3b4293a22ea8b232c1f8f52cb2f52b103c9f138f0ddc013a" }, "receives_num_hours": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "0642ec47ee7acd2528cdab7d343ddba11cbc84db", "lines": [ 7, 24, 59, 62, 122, 162 ], "path": "src/run_task.sh", "raw_sha256": "10b0238018f202209c06f12ff05d021a0ca03b98d42c86a65e80cacd4fbe7033" }, "request_gpus_binding": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "ea7f8790b97301dcdb6f3c104c5555d7ddf4e06a", "lines": [ 10 ], "path": "src/commit_utils/single_task.sub", "raw_sha256": "f8ee12da42fdebfc3b4293a22ea8b232c1f8f52cb2f52b103c9f138f0ddc013a" }, "solve_timeout_formula": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "0642ec47ee7acd2528cdab7d343ddba11cbc84db", "lines": [ 122 ], "path": "src/run_task.sh", "raw_sha256": "10b0238018f202209c06f12ff05d021a0ca03b98d42c86a65e80cacd4fbe7033" }, "timeout_grace_minutes": { "commit": "d3496fa7d5788a007d6cd143167471ccdfc688d0", "git_object_sha1": "0642ec47ee7acd2528cdab7d343ddba11cbc84db", "lines": [ 122 ], "path": "src/run_task.sh", "raw_sha256": "10b0238018f202209c06f12ff05d021a0ca03b98d42c86a65e80cacd4fbe7033" } }, "task_dir_10h_suffix": true, "timeout_formula_found": true, "timeout_grace_minutes": 5 }, "recognized_root_cell_pairs": 1313, "recognized_root_count": 47, "recognized_task_count": 1338, "unrecognized_dirs_count": 0 }