Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Relation MCQ on PARSE-10K (test)
Loading...
97.4
Accuracy
Ours
59.336
69.218
79.1
88.982
Mar 8, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Ours
Evaluation protocol=Fi...
2026.03
97.4
Qwen3-VL
Evaluation protocol=Ze...
2026.03
86.2
Gemini-2.5-Pro
Evaluation protocol=Ze...
2026.03
85
GPT-5
Evaluation protocol=Ze...
2026.03
82.1
Claude-Opus-4
Evaluation protocol=Ze...
2026.03
80.3
Robobrain2.0
Evaluation protocol=Ze...
2026.03
60.8
Feedback
Search any
task
Search any
task