Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LLM Alignment Evaluation on AlpacaEval 2.0 (test)

30.35LC Win Rate

OTPO

2.66529.852617.0424.2274May 18, 2025Jun 30, 2025Aug 12, 2025Sep 24, 2025Nov 6, 2025Dec 19, 2025Feb 1, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.05
30.3528.21,839
2025.05
29.6429.541,991
2025.05
29.2328.761,955
2025.05
29.0325.68411
2025.05
28.9328.81,961
2025.05
28.6628.341,940
2025.05
28.6228.521,954
2025.05
28.5527.831,924
2025.05
28.5528.541,956
2025.05
28.4828.131,946
2025.05
28.2322.531,654
2025.05
28.2228.96444
2025.05
28.2225.841,815
2025.05
28.0329.32435
2025.05
27.9127.451,945
2025.05
27.7227.821,951
2025.05
27.5328.35438
2025.05
27.4527.69443
2025.05
27.4327.411,963
2025.05
27.3125.311,844
2025.05
27.2524.781,775
2025.05
27.2226.821,937
2025.05
27.0725.82459
2025.05
26.9527.161,991
2025.05
26.8427.77459
2025.05
26.7727.251,984
2025.05
26.3327.77441
2025.05
25.0226.062,021
2025.05
24.5726.6426
2025.05
24.2624.5414
2025.05
23.8924.86419
2025.05
23.7623.95411
2025.05
23.56221,906
2025.05
22.9222.571,899
2025.05
21.9421.75409
2025.05
20.9822.2418
2025.05
19.7122.062,074
2025.05
18.2620.752,105
2025.05
17.7415.051,630
2025.05
17.3220.152,107
2025.05
16.9319.622,100
2025.05
16.8220.12,145
2025.05
16.7519.472,112
2026.02
14.4236.65-
2026.02
9.3716.77-
2026.02
8.1313.91-
2026.02
6.1611.93-
2026.02
4.567.45-
2026.02
4.534.04-
2026.02
4.258.45-
2026.02
3.7310.19-