{ "model": "qev_0p8b", "date": "2026-10-05", "full_suite": { "decision_dev": { "correct": 1211, "total": 1468, "accuracy": 0.8249318801089919, "rejected": 0 }, "transfer_dev": { "correct": 503, "total": 764, "accuracy": 0.6583769633507853, "rejected": 0 }, "mmlupro": { "correct": 247, "total": 1000, "accuracy": 0.247, "rejected": 0 }, "semif": { "correct": 190, "total": 252, "accuracy": 0.753968253968254, "rejected": 0 }, "scienthoon": { "correct": 596, "total": 873, "accuracy": 0.6827033218785796, "rejected": 0 }, "wanli": { "correct": 169, "total": 256, "accuracy": 0.66015625, "rejected": 0 }, "public": { "correct": 169, "total": 231, "accuracy": 0.7316017316017316, "rejected": 0 } }, "matched_subsets": { "decision_dev_all": { "correct": 1211, "total": 1468 }, "decision_dev_clean": { "correct": 1029, "total": 1264 }, "transfer_dev_all": { "correct": 503, "total": 764 }, "transfer_dev_clean": { "correct": 431, "total": 656 }, "semif_handwritten": { "correct": 109, "total": 144 }, "mmlupro": { "correct": 247, "total": 1000 }, "scienthoon": { "correct": 596, "total": 873 }, "wanli": { "correct": 169, "total": 256 }, "jevbench_public": { "correct": 169, "total": 231 } } }