Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following on IFEval (Normalized performance)
Loading...
95.8
Normalized performance
Iso-CTS
35.168
50.909
66.65
82.391
Jun 15, 2026
Normalized performance
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized performance
Iso-CTS
Category=State-of-the-...
2026.06
95.8
ColD Fusion
Category=Iterative / F...
2026.06
91.7
ConsensusTA
Category=Conventional...
2026.06
91.7
METIS
Category=Ours, Backbon...
2026.06
91.7
FedMerge
Category=Iterative / F...
2026.06
87.5
q-FedAvg
Category=Iterative / F...
2026.06
87.5
Iso-C
Category=State-of-the-...
2026.06
79.2
DARE
Category=Conventional...
2026.06
79.2
TIES
Category=Conventional...
2026.06
79.2
TSV-M
Category=State-of-the-...
2026.06
75
TULU 3
Category=Data-Mixing,...
2026.06
54.2
TA + Subspace Boosting
Category=State-of-the-...
2026.06
45.8
Task Arithmetic
Category=Conventional...
2026.06
37.5
Feedback
Search any
task
Search any
task