Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn Instruction Following on MultiIF (Accuracy)
Loading...
91.28
Accuracy
AAPA
56.2528
65.3464
74.44
83.5336
Sep 29, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
AAPA
Parameters=4B
2025.09
91.28
Qwen3 Model
Parameters=235B-2507
2025.09
90.37
Qwen3 Model
Parameters=8B
2025.09
86.69
Qwen3 Model
Parameters=32B
2025.09
85.79
Qwen3 Model
Parameters=4B-2507
2025.09
85.09
Qwen3 Model
Parameters=4B
2025.09
82
AAPA
Parameters=0.6B
2025.09
76.73
Qwen3 Model
Parameters=1.7B
2025.09
68.44
Qwen3 Model
Parameters=0.6B
2025.09
57.6
Feedback
Search any
task
Search any
task