Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
IQ-style Reasoning on MM-IQ
Loading...
29.1
Math Score
LLaVA-OneVision-Qwen2-7B
21.82
23.71
25.6
27.49
Jan 31, 2026
Math Score
Logical Operation Score
2D Geometry Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Math Score
Logical Operation Score
2D Geometry Score
LLaVA-OneVision-Qwen2-7B
Parameters=7B
2026.01
29.1
23.5
25
Ours (SFT)
Training=SFT
2026.01
27.4
24.6
23
Janus-Pro-7B
Parameters=7B
2026.01
26.5
19.6
22.7
Ours (RL)
Training=RL
2026.01
26.3
25.9
26.5
MM-EurekaQwen-7B
Parameters=7B
2026.01
25.1
23.7
24.9
Qwen2.5-VL-7B-Instruct
Parameters=7B, Variant...
2026.01
24.5
24.4
25.2
Thyme
2026.01
24.1
20.6
23
InternVL2.5-8B
Parameters=8B
2026.01
22.1
22.4
21.1
R1-onevision-RL
Training=RL
2026.01
22.1
22.4
21.1
Feedback
Search any
task
Search any
task