{"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/Qwen3.5-0.8B-Base","parameters":852985920,"revision":"dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68","source":"https://huggingface.co/Qwen/Qwen3.5-0.8B-Base/tree/dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68","updated":1792212045}],"model":"Qwen/Qwen3.5-0.8B-Base","page":"/models/Qwen/Qwen3.5-0.8B-Base","pending":[],"results":[{"benchmark":"ARC-Challenge / Qwen3.5 same-base cohort","coverage":"full","direction":"max","evaluation_seconds":34.59673888096586,"finished":1792212045,"gpu_slot_seconds":36.270080911926925,"manifest_url":"/artifacts/584079da775396492e0ed153/manifest.json","metric":"accuracy","n":1172,"protocol_version":"codesota-qwen35-arc-challenge-v1","revision":"dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68","run_id":"584079da775396492e0ed153","run_url":"/runs/584079da775396492e0ed153","scope":"8877f1f73ee0a3c138937e07b7f6ca917f2c1d914d223e6a8ffa42b9ac8f0a47","score":0.3848122866894198,"task":"qwen35-arc-challenge-full"},{"benchmark":"ARC-Easy / Qwen3.5 same-base cohort","coverage":"full","direction":"max","evaluation_seconds":52.91594243992586,"finished":1792208716,"gpu_slot_seconds":54.67201211897191,"manifest_url":"/artifacts/50e10aaaacb3cfbbee160d77/manifest.json","metric":"accuracy","n":2376,"protocol_version":"codesota-qwen35-arc-easy-v1","revision":"dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68","run_id":"50e10aaaacb3cfbbee160d77","run_url":"/runs/50e10aaaacb3cfbbee160d77","scope":"84fe51c6790b19376ad4a234c742b80e0f73e3eb0d6a7257d48e5315d6a7c078","score":0.7053872053872053,"task":"qwen35-arc-easy-full"}],"revisions":["dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68"],"source":"https://huggingface.co/Qwen/Qwen3.5-0.8B-Base"}}