Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Short-form Question Answering on TQA (TriviaQA) (test)
Loading...
68.4
F1 Score
AGAR
33.664
42.682
51.7
60.718
Jun 11, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
AGAR
Backbone=InternVL3.5-8B
2026.06
68.4
AGAR
Backbone=GLM-4.1V-9B-T...
2026.06
68.1
VAR
Backbone=GLM-4.1V-9B-T...
2026.06
67.6
CGR
Backbone=GLM-4.1V-9B-T...
2026.06
67.4
AGLA
Backbone=GLM-4.1V-9B-T...
2026.06
67.2
Uniform
Backbone=InternVL3.5-8B
2026.06
67.1
Plain VQA
Backbone=InternVL3.5-8B
2026.06
66.5
Random
Backbone=InternVL3.5-8B
2026.06
66.4
VEA-Br
Backbone=GLM-4.1V-9B-T...
2026.06
66.4
Uniform
Backbone=GLM-4.1V-9B-T...
2026.06
65.7
VEA-Con
Backbone=InternVL3.5-8B
2026.06
65.3
Random
Backbone=GLM-4.1V-9B-T...
2026.06
65.3
VEA-Con
Backbone=GLM-4.1V-9B-T...
2026.06
65.2
Plain VQA
Backbone=GLM-4.1V-9B-T...
2026.06
65.1
VEA-Br
Backbone=InternVL3.5-8B
2026.06
62.8
AGLA
Backbone=InternVL3.5-8B
2026.06
61.7
VAR
Backbone=InternVL3.5-8B
2026.06
59.5
CGR
Backbone=InternVL3.5-8B
2026.06
35
Feedback
Search any
task
Search any
task