Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Table Reasoning on MMQA (test)
Loading...
50
Accuracy
CPO
17.76
26.13
34.5
42.87
Jun 3, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
CPO
Model=Qwen3-14B-Base
2026.06
50
CPO
Model=Mistral-8B-Instruct
2026.06
43
CPO
Model=Llama-3.1-8B-Ins...
2026.06
42
Trace SFT
Model=Llama-3.1-8B-Ins...
2026.06
38
Table-R1
Model=Table-R1
2026.06
33.6
Trace SFT
Model=Qwen3-14B-Base
2026.06
32
Trace SFT
Model=Mistral-8B-Instruct
2026.06
32
Q&A SFT
Model=Mistral-8B-Instruct
2026.06
30
Q&A SFT
Model=Qwen3-14B-Base
2026.06
29
Q&A SFT
Model=Llama-3.1-8B-Ins...
2026.06
28
DPO
Model=Qwen3-14B-Base
2026.06
21
DPO
Model=Llama-3.1-8B-Ins...
2026.06
20.9
DPO
Model=Mistral-8B-Instruct
2026.06
19
Feedback
Search any
task
Search any
task