Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Intent Understanding on IntentQA
Loading...
48.6
LLM-Judge Accuracy
OMNISAPIENS-7B RL
16.464
24.807
33.15
41.493
Oct 6, 2025
LLM-Judge Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
LLM-Judge Accuracy
OMNISAPIENS-7B RL
Method variant=RL
2025.10
48.6
HumanOmniV2-7B
Model size=7B
2025.10
26.3
OMNISAPIENS-7B SFT
Method variant=SFT
2025.10
25.6
Qwen 2.5-Omni-7B
Model size=7B
2025.10
25.4
Qwen-2.5-VL-7B
Model size=7B
2025.10
24.9
Gemma-3-4B
Model size=4B
2025.10
22.7
OMNISAPIENS-7B BAM
Method variant=BAM
2025.10
17.7
Feedback
Search any
task
Search any
task