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

General Language Model Evaluation on MMLU, BBH, TruthfulQA, TriviaQA, and AlpacaEval

68.93MMLU

ELUDe

38.520446.415254.3162.2048Apr 15, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
68.9322.3839.7528.596.1453
2026.04
68.7931.333840.776.0383
2026.04
68.7940.939.527.36.1676
2026.04
68.7134.4137.542.456.0307
2026.04
68.6440.937.7539.856.0196
2026.04
68.6443.0638.529.696.1099
2026.04
68.5731.4839.2526.76.1704
2026.04
68.5743.0638.2544.085.9923
2026.04
68.5734.2638.537.526.0251
2026.04
68.4942.1338.7537.716.0951
2026.04
68.4939.9737.541.136.0506
2026.04
68.4243.8339.7524.66.1535
2026.04
68.4238.5844.7515.466.4073
2026.04
68.3542.943.2516.426.3429
2026.04
68.2740.123922.536.2853
2026.04
68.234.4138.2545.155.8489
2026.04
67.8443.3637.7535.066.0679
2026.04
42.426.5428.7540.566.2993
2026.04
42.1120.992946.586.2765
2026.04
42.0319.752946.46.2686
2026.04
41.9623.583032.916.3436
2026.04
41.7428.0927.7549.16.2556
2026.04
41.6724.3831.7532.326.3341
2026.04
41.6710.0331.7531.516.3354
2026.04
41.5927.4130.524.696.3499
2026.04
41.5214.6633.528.26.3393
2026.04
41.5220.8328.545.176.2774
2026.04
41.3720.2229.2540.536.3267
2026.04
41.325.1530.529.556.3446
2026.04
41.2324.383316.566.3849
2026.04
40.521.630.537.186.3051
2026.04
39.8421.9130.537.086.2991
2026.04
39.7718.6735.2515.266.393
2026.04
39.6923.4630.2536.756.3109