{"api_version":"codesota.v1","data":{"archived_results":[],"evidence_status":"CodeSOTA measurements only; model-card claims are not benchmark results","measured_parameters":[{"basis":"Unique parameters counted in the loaded evaluator model on White","model":"Qwen/Qwen2.5-Coder-1.5B","parameters":1543714304,"revision":"df3ce67c0e24480f20468b6ef2894622d69eb73b","source":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B/tree/df3ce67c0e24480f20468b6ef2894622d69eb73b","updated":1792208129}],"model":"Qwen/Qwen2.5-Coder-1.5B","page":"/models/Qwen/Qwen2.5-Coder-1.5B","pending":[],"results":[{"benchmark":"HumanEval (full 164, serial greedy pass@1)","coverage":"full","direction":"max","evaluation_seconds":526.0397081909468,"finished":1792208129,"gpu_slot_seconds":527.4325542700244,"manifest_url":"/artifacts/2d80929f0ec5f26de33e4a98/manifest.json","metric":"pass@1","n":164,"protocol_version":"codesota-humaneval-full-v2","revision":"df3ce67c0e24480f20468b6ef2894622d69eb73b","run_id":"2d80929f0ec5f26de33e4a98","run_url":"/runs/2d80929f0ec5f26de33e4a98","scope":"7388be4229d45cb22b346201154469558e2015772bcb2abde7f2fb7b0b7ad294","score":0.3719512195121951,"task":"code-generation-full"}],"revisions":["df3ce67c0e24480f20468b6ef2894622d69eb73b"],"source":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B"}}