Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following on Muses-Bench Aligned n=187
Loading...
93.16
Accuracy
Deepseek
40.2032
53.9516
67.7
81.4484
Jun 20, 2026
Accuracy
W.Acc
Per-User Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
W.Acc
Per-User Accuracy
Deepseek
Framework=Muses-Bench,...
2026.06
93.16
93.24
94.07
Qwen
Framework=Muses-Bench,...
2026.06
91.36
91.86
91.36
Gemini
Framework=Muses-Bench,...
2026.06
83.35
83.32
82.78
GPT
Framework=Muses-Bench,...
2026.06
42.24
56.07
54.55
Feedback
Search any
task
Search any
task