Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Chat on AlpacaEval LC 2
Loading...
84.3
LC Win Rate
Qwen 3 VL 32B Instruct
2.972
24.086
45.2
66.314
Dec 15, 2025
Jan 9, 2026
Feb 3, 2026
Feb 28, 2026
Mar 25, 2026
Apr 19, 2026
May 14, 2026
LC Win Rate
Updated 16d ago
Evaluation Results
Method
Method
Links
LC Win Rate
Qwen 3 VL 32B Instruct
Parameters=32B
2025.12
84.3
Qwen 2.5 32B
Parameters=32B
2025.12
81.9
Olmo 3.1 32B Instruct
Stage=DPO
2025.12
69.7
Qwen 3 32B
Thinking=No, Parameter...
2025.12
67.9
Gemma 3 27B
Parameters=27B
2025.12
65.5
Olmo 3.1 32B Instruct
Stage=Final Instruct 3.1
2025.12
59.8
Olmo 3.1 32B Instruct
Stage=SFT
2025.12
42.2
Gemma 2 27B
Parameters=27B
2025.12
39.8
OLMo 2 32B
Parameters=32B
2025.12
38
Qwen2.5-3B-GRLO
Backbone=Qwen2.5-3B, T...
2026.05
35.7
Qwen2.5-3B-GRLO+RLVR
Backbone=Qwen2.5-3B, T...
2026.05
29.8
Qwen2.5-3B-Instruct
Backbone=Qwen2.5-3B, T...
2026.05
24.2
Apertus 70B
Parameters=70B
2025.12
19.9
Qwen2.5-3B-RLVR
Backbone=Qwen2.5-3B, T...
2026.05
12.3
Qwen2.5-3B-MathSFT
Backbone=Qwen2.5-3B, T...
2026.05
8.4
Qwen2.5-3B-Base
Backbone=Qwen2.5-3B, T...
2026.05
6.1
Feedback
Search any
task
Search any
task