{ "AUBIN-12B full precision (think)": { "kev_transfer_test": { "n": 656, "accuracy": 0.878, "brier": 0.1991, "ece15": 0.0628, "nll": 0.4183 }, "kev_test": { "n": 1200, "accuracy": 0.835, "brier": 0.2587, "ece15": 0.0451, "nll": 0.7674 } }, "AUBIN-31B (fast, one pass)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8979, "brier": 0.1782, "ece15": 0.0782, "nll": 0.3786 }, "kev_test": { "n": 1200, "accuracy": 0.8375, "brier": 0.252, "ece15": 0.0698, "nll": 0.7191 } }, "AUBIN-31B (think)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8902, "brier": 0.1799, "ece15": 0.0339, "nll": 0.3655 }, "kev_test": { "n": 1200, "accuracy": 0.8458, "brier": 0.2467, "ece15": 0.0344, "nll": 0.7547 } }, "AUBIN Duo (31B + 12B, think)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8933, "brier": 0.1694, "ece15": 0.055, "nll": 0.3528 }, "kev_test": { "n": 1200, "accuracy": 0.85, "brier": 0.238, "ece15": 0.0252, "nll": 0.7524 } }, "AUBIN Duo (31B + 12B full precision, think)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8948, "brier": 0.1688, "ece15": 0.0398, "nll": 0.3492 }, "kev_test": { "n": 1200, "accuracy": 0.8458, "brier": 0.2386, "ece15": 0.0281, "nll": 0.7185 } }, "AUBIN Duo-SC (31B self-consistent think + 12B full precision)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8948, "brier": 0.1681, "ece15": 0.046, "nll": 0.3486 }, "kev_test": { "n": 1200, "accuracy": 0.8425, "brier": 0.2391, "ece15": 0.035, "nll": 0.7191 } }, "AUBIN Trio (31B-SC + 12B full precision + Phi-4)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8887, "brier": 0.169, "ece15": 0.0384, "nll": 0.3472 }, "kev_test": { "n": 1200, "accuracy": 0.8508, "brier": 0.2369, "ece15": 0.0223, "nll": 0.6749 } }, "AUBIN Quad (31B-SC + 12B full precision + Phi-4 + Mistral-Small)": { "kev_transfer_test": { "n": 656, "accuracy": 0.8857, "brier": 0.1678, "ece15": 0.053, "nll": 0.3481 } } }