Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Complex Instruction Following on Internal Evaluation
Loading...
0
Tie Score
DeepSeek-V4-Pro
-0.001
-0.0005
0
0.0005
Apr 26, 2026
Tie Score
DS Score
Opus Score
DS Rate
Opus Rate
Tie Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Tie Score
DS Score
Opus Score
DS Rate
Opus Rate
Tie Rate
DeepSeek-V4-Pro
2026.04
0
23
-
46.9
-
0
Claude-Opus-4.5
2026.04
0
-
26
-
53.1
0
Feedback
Search any
task
Search any
task