Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following on Muses-Bench Conflict n=368
Loading...
86.98
Accuracy
Deepseek
28.6048
43.7599
58.915
74.0701
Jun 20, 2026
Accuracy
Weighted Accuracy
Per-User Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Weighted Accuracy
Per-User Accuracy
Deepseek
Framework=Muses-Bench,...
2026.06
86.98
87.22
15.57
Qwen
Framework=Muses-Bench,...
2026.06
85.05
85.05
15.21
Gemini
Framework=Muses-Bench,...
2026.06
58.11
66.61
11.73
GPT
Framework=Muses-Bench,...
2026.06
30.85
43.84
7.92
Feedback
Search any
task
Search any
task
