Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Examination on MMLU-Pro
Loading...
0.7709
Score
Qwen3-VL Thinking
0.63726
0.671955
0.70665
0.741345
Jan 14, 2026
Jan 23, 2026
Feb 1, 2026
Feb 10, 2026
Feb 19, 2026
Feb 28, 2026
Mar 10, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Qwen3-VL Thinking
Number of Parameters=8B
2026.01
0.7709
InternVL 3.5
Number of Parameters=8B
2026.01
0.7603
STEP3-VL-10B
Number of Parameters=10B
2026.01
0.7602
Qwen3-8B
Inference Mode=think
2026.03
0.7434
MiMo-VL RL-2508
Number of Parameters=7B
2026.01
0.7381
SSA-LLM-8B
Inference Mode=think
2026.03
0.7315
GLM-4.6V Flash
Number of Parameters=9B
2026.01
0.723
SSA-LLM-8B
Inference Mode=no-think
2026.03
0.6713
Qwen3-8B
Inference Mode=no-think
2026.03
0.6424
Feedback
Search any
task
Search any
task