Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Table Reasoning on FinQA (Pass@1)
Loading...
39.7
Pass@1
TAC
-1.172
9.439
20.05
30.661
Jun 23, 2026
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
TAC
Backbone=Qwen3-4B-Base...
2026.06
39.7
SEC
Backbone=Qwen3-4B-Base...
2026.06
38.9
Random
Backbone=Qwen3-4B-Base...
2026.06
37
TAC
Backbone=Qwen3-1.7B
2026.06
25.6
M2O
Backbone=Qwen3-1.7B
2026.06
24.7
Random
Backbone=Qwen3-1.7B
2026.06
24.3
SEC
Backbone=Qwen3-1.7B
2026.06
23.2
TAC
Backbone=Llama3.2-3B
2026.06
21.7
M2O
Backbone=Llama3.2-3B
2026.06
19.2
Base
Backbone=Llama3.2-3B
2026.06
15.6
SEC
Backbone=Llama3.2-3B
2026.06
15.4
Random
Backbone=Llama3.2-3B
2026.06
14.2
Base
Backbone=Qwen3-1.7B
2026.06
9.7
TAC
Backbone=Qwen3-0.6B-Ba...
2026.06
4.5
SEC
Backbone=Qwen3-0.6B-Ba...
2026.06
3.8
Random
Backbone=Qwen3-0.6B-Ba...
2026.06
0.4
Feedback
Search any
task
Search any
task