Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Language Model Evaluation on Tulu-3 (dev)

60.85Knowledge Score

Equal

22.463632.429342.39552.3607Jul 1, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.07
60.8564.5559.0353.6168.5853.4960.02
2026.07
60.2565.6959.4244.2263.5954.8358
2026.07
60.2452.3654.768.6744.3660.4756.8
2026.07
59.668.1263.3755.7658.0455.9460.14
2026.07
59.3562.8858.6364.4367.4760.9562.28
2026.07
59.1563.760.6254.0570.2454.3560.35
2026.07
59.0868.7765.9961.5544.9256.4359.46
2026.07
58.0263.257.3557.2868.2152.7559.47
2026.07
57.1464.0358.5165.5268.2157.6561.84
2026.07
51.6367.3756.1457.9168.3946.3957.97
2026.07
29.932.1435.8434.130.3111.1428.9
2026.07
29.8131.722.933.435.325.3429.74
2026.07
29.4531.326.3732.438.8225.9530.71
2026.07
29.3431.8426.6835.0216.6417.2626.13
2026.07
28.8630.9122.5130.6835.8626.1929.17
2026.07
28.7330.6324.6730.4842.5143.4533.41
2026.07
28.6530.7424.3534.6230.512.6126.91
2026.07
28.5930.525.1836.0633.6410.2827.37
2026.07
28.5831.1222.1433.6139.7426.5630.29
2026.07
28.5730.1927.0234.3224.2116.6526.82
2026.07
28.4631.9830.4133.520.1523.3827.98
2026.07
28.3932.9823.9632.137.8927.7830.51
2026.07
28.3731.3124.6729.5738.6326.9329.91
2026.07
28.3130.9627.6430.9742.5136.4732.81
2026.07
28.0729.2821.5936.0646.9525.0931.78
2026.07
28.0731.8822.4226.941.5941.3732.04
2026.07
27.9329.6823.5627.7643.8150.9233.94
2026.07
27.7431.7524.2531.838.6341.6232.63
2026.07
27.729.6620.5834.5342.8832.9331.38
2026.07
27.6529.823.323333.8314.5727.03
2026.07
27.530.5325.4133.126.0623.6227.7
2026.07
27.2930.0425.5331.2817.0132.5627.28
2026.07
27.2730.2327.7734.9434.9414.8127.85
2026.07
24.929.9430.2525.4625.3222.5226.4
2026.07
23.9424.429.6723.8117.9322.6431.17