Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Figure Reconstruction on VFig-Bench Human Evaluation (test)
Loading...
1,852.5
Mean Elo Rating
Gemini 3 Pro
1,024.556
1,239.503
1,454.45
1,669.397
Mar 25, 2026
Mean Elo Rating
Elo Rating Std Dev
Updated 24d ago
Evaluation Results
Method
Method
Links
Mean Elo Rating
Elo Rating Std Dev
Gemini 3 Pro
2026.03
1,852.5
36.3
GPT 5.2
2026.03
1,617.3
35.9
VFig
2026.03
1,473.8
38.2
Qwen3-VL-4B
2026.03
1,056.4
35.4
Feedback
Search any
task
Search any
task