Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Downstream Evaluation on All Downstream Tasks 15 tasks
Loading...
36.4
Average Accuracy (All Tasks)
MIDAS
19.76
24.08
28.4
32.72
Sep 27, 2024
Average Accuracy (All Tasks)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy (All Tasks)
MIDAS
Parameters=8B, d(i)/i...
2024.09
36.4
MIDAS
Parameters=2B, d(i)/i...
2024.09
32.9
Baseline
Parameters=8B, d(i)/i...
2024.09
32.8
MIDAS
Parameters=2B, d(i)/i...
2024.09
29.5
MIDAS
Parameters=1B, d(i)/i...
2024.09
28.3
Baseline
Parameters=2B, d(i)/i...
2024.09
28
MIDAS
Parameters=1B, d(i)/i...
2024.09
27.5
MIDAS
Parameters=1B, d(i)/i...
2024.09
26.8
MIDAS
Parameters=1B, d(i)/i...
2024.09
26.7
GRADSTACK
Parameters=2B, d(i)/i...
2024.09
25.9
MIDAS
Parameters=1B, d(i)/i...
2024.09
25.6
Baseline
Parameters=1B, d(i)/i...
2024.09
24
GRADSTACK
Parameters=1B, d(i)/i...
2024.09
22.6
GRADSTACK
Parameters=1B, d(i)/i...
2024.09
20.4
Feedback
Search any
task
Search any
task