Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Instruction Following Evaluation on MM-IFE
Loading...
14.8
MM-IFE Score
POW3R dynamic
5.648
8.024
10.4
12.776
May 19, 2026
MM-IFE Score
Updated 14d ago
Evaluation Results
Method
Method
Links
MM-IFE Score
POW3R dynamic
Base policy=Qwen3-VL-8B
2026.05
14.8
Category-balanced
Base policy=Qwen3-VL-8B
2026.05
14.2
POW3R dynamic
Base policy=Qwen3-VL-4B
2026.05
13.5
Static scalar
Base policy=Qwen3-VL-8B
2026.05
13.5
Category-balanced
Base policy=Qwen3-VL-4B
2026.05
13
Static scalar
Base policy=Qwen3-VL-4B
2026.05
12.5
Base
Base policy=Qwen3-VL-8B
2026.05
12.5
Binary
Base policy=Qwen3-VL-8B
2026.05
12.3
Binary
Base policy=Qwen3-VL-4B
2026.05
11.8
Base
Base policy=Qwen3-VL-4B
2026.05
11.5
POW3R dynamic
Base policy=Gemma3-4B
2026.05
7.2
Category-balanced
Base policy=Gemma3-4B
2026.05
6.7
Static scalar
Base policy=Gemma3-4B
2026.05
6.3
Binary
Base policy=Gemma3-4B
2026.05
6.1
Base
Base policy=Gemma3-4B
2026.05
6
Feedback
Search any
task
Search any
task