Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Quality-judgment accuracy on LLMBar ZH condition
Loading...
86.5
Strict Accuracy (%)
DeepSeek
71.108
75.104
79.1
83.096
Jun 12, 2026
Strict Accuracy (%)
Tie-Half Accuracy (%)
Tie-Half Accuracy 95% CI (Lower Bound)
Position-A Rate (%)
Tie Rate (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Strict Accuracy (%)
Tie-Half Accuracy (%)
Tie-Half Accuracy 95% CI (Lower Bound)
Position-A Rate (%)
Tie Rate (%)
DeepSeek
Language condition=ZH,...
2026.06
86.5
87.8
85.6
53.1
2.5
Gemini Flash
Language condition=ZH,...
2026.06
83.3
83.7
81.2
56.9
0.8
Claude Haiku
Language condition=ZH,...
2026.06
74
74.3
71.4
53
0.7
GPT-4.1 Mini
Language condition=ZH,...
2026.06
71.7
72.8
69.8
52.6
2.1
Feedback
Search any
task
Search any
task