Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Knowledge Evaluation on OpenBookQA (test)
Loading...
92.31
Accuracy
Qwen3-Omni-Instruct
47.9644
59.4772
70.99
82.5028
Feb 15, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-Omni-Instruct
Type=Omni, Size=30B-A3B
2026.02
92.31
Kimi-Audio-7B-Instruct
Type=Audio, Size=7B
2026.02
84.18
Qwen2.5-Omni-7B
Type=Omni, Size=7B
2026.02
81.53
MiniCPM-o
Type=Omni, Size=9B
2026.02
79.12
Qwen2.5-Omni-3B
Type=Omni, Size=3B
2026.02
77.36
Step-Audio-2-mini
Type=Audio, Size=8B
2026.02
75.6
Ming-Lite-Omni-1.5
Type=Omni, Size=19B-A2.8B
2026.02
69.67
Eureka-Audio-Instruct
Type=Ours, Size=1.7B
2026.02
69.23
Audio Flamingo 3
Type=Audio, Size=8B
2026.02
61.54
Eureka-Audio-Base
Type=Ours, Size=1.7B
2026.02
52.53
Qwen2-Audio
Type=Audio, Size=7B
2026.02
49.67
Feedback
Search any
task
Search any
task