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

Chat on AlpacaEval 2.0 (test)

57.46AlpacaEval (LC win %)

GPT-4o

1.903216.326630.7545.1734Aug 27, 2024Nov 21, 2024Feb 16, 2025May 14, 2025Aug 9, 2025Nov 4, 2025Jan 30, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.08
57.4651.33--
2026.01
35.639.42,011-
2026.01
34.538.22,011-
2026.01
3233.92,250-
2026.01
31.534.32,278-
2026.01
3131.82,150-
2026.01
30.532.22,172-
2024.08
29.6126.69--
2026.01
29.532.62,216-
2026.01
29.331.82,192-
2026.01
28.730.72,289-
2026.01
28.430.22,186-
2024.08
26.7822.69--
2024.08
25.8522.5--
2026.01
25.830.92,871-
2026.01
25.6272,261-
2026.01
24.831.22,911-
2026.01
24.427.42,366-
2026.01
23.527.83,050-
2026.01
23.2272,950-
2024.08
22.922.6--
2026.01
22.928.23,101-
2026.01
22.922.61,899-
2026.01
22.827.42,992-
2024.08
22.7519.01--
2024.08
22.714.1--
2026.01
22.725.63,012-
2026.01
21.9263,174-
2026.01
21.825.12,916-
2026.01
21.426.43,252-
2024.08
20.921.8--
2024.08
20.7617.93--
2024.08
20.6616.69--
2024.08
20.2516.88--
2024.08
18.9921.55--
2024.08
18.9721.22--
2026.01
17.419.43,317-
2024.08
17.1613.11--
2026.01
15.820.53,154-
2026.01
15.515.82,218-
2024.08
15.3212.96--
2024.08
14.4910.88--
2024.08
13.5715.54--
2024.08
13.210.99--
2024.08
12.6114.34--
2024.08
4.042.15--
2025.12
---32.6
2025.12
---10.4
2025.12
---24.6
2025.12
---17.6
2025.12
---12.5
2025.12
---18
2025.12
---14.9
2025.12
---27
2025.12
---37.2
2025.12
---14.5
2025.12
---32.1
2025.12
---25.8
2025.12
---19.3
2025.12
---24.7
2025.12
---20.6
2025.12
---33.4