Our new X account is live! Follow @wizwand_team for updates

Multi-turn Dialogue on TSEData

96.46Accuracy

ChatAD-Mistral-7B

Updated 4d ago

Evaluation Results

Method	Links
ChatAD-Mistral-7B 2026.01		96.46	96.32	3.9
ChatAD* 2026.01		96.07	95.83	2.19
ChatAD-Qwen2.5-7B 2026.01		95.69	95.39	1.95
ChatAD-Llama3-8B 2026.01		82.38	83.96	27.7
TimeMQA-Llama3-8B 2026.01		75.77	77.38	33.74
TimeMQA-Qwen2.5-7B 2026.01		70.3	71.74	37.32
Mistral-7B-Instruct 2026.01		70.17	75.7	53.03
Llama3-8B-Instruct 2026.01		69.63	73.88	48.66
Qwen2.5-7B-Instruct 2026.01		69.42	73.31	47.32
TimeMQA-Mistral-7B 2026.01		66.11	67.11	40.47
Qwen3-8B 2026.01		60.86	70.66	69.98
DeepSeek-R1-Distill-Llama3-8B 2026.01		60.18	68.12	66.25
DeepSeek-R1-Distill-Qwen2.5-7B 2026.01		50.99	65.87	92.77