Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Table Question Answering on TableBench (test)
Loading...
0.4887
Overall Accuracy
Llama-3.1-405B-Instruct + TCoT
0.366812
0.398456
0.4301
0.461744
May 18, 2026
Overall Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Overall Accuracy
Llama-3.1-405B-Instruct + TCoT
# Params.=405B
2026.05
0.4887
Qwen2.5-72B-Instruct + TCoT
# Params.=72B
2026.05
0.4879
Qwen3-8B + TGN
# Params.=8B
2026.05
0.4846
Llama-4-Scout-17B-16E-Instruct + TCoT
# Params.=17B
2026.05
0.4653
Qwen2.5-Coder-32B-Instruct + TCoT
# Params.=32B
2026.05
0.4551
QWQ-32B + DP
# Params.=32B
2026.05
0.4387
Llama3.1-70B-Instruct + TCoT
# Params.=70B
2026.05
0.4105
Llama3-70B-Chat + TCoT
# Params.=70B
2026.05
0.3868
DeepSeek-R1-Distill-Llama-8B + PIP
# Params.=8B
2026.05
0.3748
GPT-3.5-Turbo + PoT
2026.05
0.3715
Feedback
Search any
task
Search any
task