{"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":"mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview","parameters":752393024,"revision":"558fc651bf01bbe7cf306ebf2fb32032d7b4e818","source":"https://huggingface.co/mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview/tree/558fc651bf01bbe7cf306ebf2fb32032d7b4e818","updated":1792212298}],"model":"mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview","page":"/models/mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview","pending":[],"results":[{"benchmark":"ARC-Challenge / Qwen3.5 same-base cohort","coverage":"full","direction":"max","evaluation_seconds":31.552993295015767,"finished":1792212298,"gpu_slot_seconds":33.21164660400245,"manifest_url":"/artifacts/4d3599a2d9c1a839e8fb80e2/manifest.json","metric":"accuracy","n":1172,"protocol_version":"codesota-qwen35-arc-challenge-v1","revision":"558fc651bf01bbe7cf306ebf2fb32032d7b4e818","run_id":"4d3599a2d9c1a839e8fb80e2","run_url":"/runs/4d3599a2d9c1a839e8fb80e2","scope":"8877f1f73ee0a3c138937e07b7f6ca917f2c1d914d223e6a8ffa42b9ac8f0a47","score":0.34897610921501704,"task":"qwen35-arc-challenge-full"},{"benchmark":"ARC-Easy / Qwen3.5 same-base cohort","coverage":"full","direction":"max","evaluation_seconds":90.58761629799847,"finished":1792209235,"gpu_slot_seconds":92.2507922439836,"manifest_url":"/artifacts/90fc3dc17e1dce5bd5504311/manifest.json","metric":"accuracy","n":2376,"protocol_version":"codesota-qwen35-arc-easy-v1","revision":"558fc651bf01bbe7cf306ebf2fb32032d7b4e818","run_id":"90fc3dc17e1dce5bd5504311","run_url":"/runs/90fc3dc17e1dce5bd5504311","scope":"84fe51c6790b19376ad4a234c742b80e0f73e3eb0d6a7257d48e5315d6a7c078","score":0.6691919191919192,"task":"qwen35-arc-easy-full"}],"revisions":["558fc651bf01bbe7cf306ebf2fb32032d7b4e818"],"source":"https://huggingface.co/mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview"}}