Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Wide-Baseline Correspondence Reasoning on ReasonMatch-Bench DL3DV high-divergence
Loading...
93.5
F1 Score
Human
19.348
38.599
57.85
77.101
Jun 2, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Human
2026.06
93.5
DCRL
2026.06
57.7
GPT-5-mini
2026.06
35.9
Gemini-2.5-Pro
2026.06
26.5
Qwen3-VL-235B
2026.06
25.3
Claude-4.5-Sonnet
2026.06
22.2
Feedback
Search any
task
Search any
task