Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Reasoning on MMStar
Loading...
74.7
Accuracy
DAPO + ReMind
44.9456
52.6703
60.395
68.1197
May 29, 2026
May 30, 2026
May 31, 2026
Jun 1, 2026
Jun 2, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
DAPO + ReMind
Base Model=Qwen3-VL-8B...
2026.06
74.7
GRPO + ReMind
Base Model=Qwen3-VL-8B...
2026.06
73.4
DAPO
Base Model=Qwen3-VL-8B...
2026.06
72.77
RePO
Base Model=Qwen3-VL-8B...
2026.06
72.6
RLEP
Base Model=Qwen3-VL-8B...
2026.06
72.27
GRPO
Base Model=Qwen3-VL-8B...
2026.06
72.2
ExGRPO
Base Model=Qwen3-VL-8B...
2026.06
72
Base Model
Base Model=Qwen3-VL-8B...
2026.06
71.83
ETTC
Aggregation Strategy=E...
2026.05
60.07
Voting
Aggregation Strategy=M...
2026.05
59.27
Qwen-7B
Model Backbone=Qwen, M...
2026.05
56.77
Gemma-12B
Model Backbone=Gemma,...
2026.05
53.4
Pixtral-12B
Model Backbone=Pixtral...
2026.05
50.35
LLaMA-11B
Model Backbone=LLaMA,...
2026.05
46.09
Feedback
Search any
task
Search any
task