{ "model": "Qev-4B", "revision": "v0.1.0", "full_suite": { "decision_dev": { "correct": 1286, "total": 1468, "accuracy": 0.8760217983651226, "rejected": 0 }, "transfer_dev": { "correct": 618, "total": 764, "accuracy": 0.8089005235602095, "rejected": 0 }, "mmlupro": { "correct": 503, "total": 1000, "accuracy": 0.503, "rejected": 0 }, "semif": { "correct": 228, "total": 252, "accuracy": 0.9047619047619048, "rejected": 0 }, "scienthoon": { "correct": 670, "total": 873, "accuracy": 0.7674684994272624, "rejected": 0 }, "wanli": { "correct": 188, "total": 256, "accuracy": 0.734375, "rejected": 0 }, "public": { "correct": 190, "total": 231, "accuracy": 0.8225108225108225, "rejected": 0 } }, "matched_subsets": { "decision_dev_all": { "correct": 1286, "total": 1468 }, "decision_dev_clean": { "correct": 1099, "total": 1264 }, "transfer_dev_all": { "correct": 618, "total": 764 }, "transfer_dev_clean": { "correct": 538, "total": 656 }, "mmlupro": { "correct": 503, "total": 1000 }, "scienthoon": { "correct": 670, "total": 873 }, "wanli": { "correct": 188, "total": 256 }, "semif_handwritten": { "correct": 130, "total": 144 }, "jevbench_public": { "correct": 190, "total": 231 } } }