Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Comparative Reasoning on delta-SNLI
Loading...
88.9
Accuracy
Always Tell Me The Odds
74.756
78.428
82.1
85.772
May 2, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Always Tell Me The Odds
Backbone=Qwen2.5-14B-I...
2025.05
88.9
Always Tell Me The Odds
Backbone=Qwen2.5-14B-I...
2025.05
86
Always Tell Me The Odds
Backbone=Qwen2.5-14B-I...
2025.05
85.1
Always Tell Me The Odds
Backbone=Qwen2.5-7B-In...
2025.05
84.4
Always Tell Me The Odds
Backbone=Qwen2.5-8B-In...
2025.05
83.3
Llama-3-Instruct
Evaluation Protocol=Pr...
2025.05
81.3
RoBERTa-L
Type=Encoder
2025.05
77.9
DeepSeek-R1-Distill-Qwen-32B
Evaluation Protocol=0-...
2025.05
77.2
GPT-4o
Evaluation Protocol=0-...
2025.05
75.3
Feedback
Search any
task
Search any
task