Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Inference on RTE Neg (accuracy)
Loading...
88.1
Accuracy (RTE Neg)
RoBERTa-large
58.876
66.463
74.05
81.637
Apr 21, 2026
Accuracy (RTE Neg)
Updated 3mo ago
Evaluation Results
Method
Method
Links
Accuracy (RTE Neg)
RoBERTa-large
# Params.=355M, Evalua...
2026.04
88.1
OpenAI o1
# Params.=—, Evaluatio...
2026.04
87.5
RoBERTa-large-NSP
# Params.=355M, Evalua...
2026.04
87.2
GPT-4o
# Params.=—, Evaluatio...
2026.04
86.9
RoBERTa-large
# Params.=355M, Evalua...
2026.04
86.2
RoBERTa-large
# Params.=355M, Evalua...
2026.04
84.7
Qwen2 7B
# Params.=7B, Evaluati...
2026.04
82.3
Llama 3.1 8B
# Params.=8B, Evaluati...
2026.04
81.3
Llama 3.1 70B
# Params.=70B, Evaluat...
2026.04
78.9
Qwen2 7B
# Params.=7B, Evaluati...
2026.04
78.3
BERTNOT
# Params.=110M, Evalua...
2026.04
74.5
Qwen2 7B
# Params.=7B, Evaluati...
2026.04
71.7
Llama 3.1 8B
# Params.=8B, Evaluati...
2026.04
65.3
Llama 3.1 8B
# Params.=8B, Evaluati...
2026.04
60
Feedback
Search any
task
Search any
task