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

Instruction Following on AlpacaEval LC 2

80.9Win Rate

Qwen 3 VL 32B Think

-1.57219.83941.2562.661Oct 10, 2025Nov 15, 2025Dec 21, 2025Jan 26, 2026Mar 3, 2026Apr 8, 2026May 14, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2025.12
80.9
2025.12
78.6
2025.12
75.6
2025.12
74.2
2025.10
69.7
2025.12
69.1
2025.12
69.1
2025.10
68.9
2025.10
68.5
2025.10
67.4
2025.10
65.3
2025.10
64.2
2025.10
63.8
2025.10
63.5
2025.10
62.3
2025.10
60.7
2025.10
58.4
2025.10
57.5
2025.10
57.2
2025.10
56.2
2025.10
54.5
2026.05
53.5
2026.05
51.1
2026.05
45.8
2025.10
43.1
2025.10
42.8
2025.10
42.5
2025.10
41.2
2025.10
39.8
2026.02
38.21
2026.02
37.61
2025.10
36.9
2025.10
36.7
2025.10
36.3
2025.10
34.5
2026.05
33.9
2026.02
33.64
2025.10
33.1
2026.05
31.5
30.8
2025.12
26.2
2026.02
25.32
2026.05
22.9
2026.02
17.24
2026.05
8.5
2026.05
8.1
2026.05
7.6
2026.05
7.3
2026.05
1.6