Argument Quality Assessment on Webis-ArgQuality 20 benchmark leaderboard · SOTA2 Research

Argument Quality Assessment on Webis-ArgQuality 20

0.473Pearson Correlation (r)Llama-70B

Evaluation Results

Method	Links
Llama-70B2026.05		0.473	0.477	0.327	0.811	1.027	0.493	52.93
Llama-70B2026.05		0.465	0.465	0.32	0.812	1.034	0.487	52.43
Qwen2.5-72B2026.05		0.463	0.466	0.319	0.817	1.036	0.467	50.82
Qwen2.5-72B2026.05		0.453	0.459	0.314	0.824	1.046	0.445	49.04
Llama-70B2026.05		0.442	0.441	0.301	0.836	1.056	0.487	52.33
Qwen2.5-72B2026.05		0.435	0.443	0.302	0.846	1.063	0.451	49.55
Olmo2-32B2026.05		0.402	0.377	0.257	0.86	1.094	0.366	42.41
Olmo2-32B2026.05		0.398	0.38	0.258	0.869	1.097	0.402	45.29
Command-R-104B2026.05		0.392	0.381	0.26	0.864	1.103	0.406	45.64
Command-R-7B2026.05		0.37	0.363	0.247	0.887	1.122	0.417	46.34
Command-R-104B2026.05		0.365	0.362	0.246	0.876	1.127	0.423	47.07
Qwen2.5-7B2026.05		0.354	0.359	0.244	0.882	1.137	0.456	49.57
Command-R-104B2026.05		0.354	0.357	0.242	0.885	1.136	0.428	47.42
Command-R-7B2026.05		0.345	0.344	0.233	0.903	1.144	0.34	40.25
Qwen2.5-7B2026.05		0.322	0.326	0.221	0.918	1.164	0.431	47.51
Command-R-7B2026.05		0.301	0.302	0.205	0.924	1.178	0.376	43.04
Olmo2-32B2026.05		0.296	0.295	0.199	0.937	1.185	0.392	44.25
Mixtral-8x22B2026.05		0.29	0.273	0.185	0.938	1.19	0.412	45.95
Llama-8B2026.05		0.258	0.263	0.176	0.968	1.218	0.373	42.68
Mixtral-8x22B2026.05		0.237	0.227	0.152	0.978	1.235	0.311	37.95
Mixtral-8x7B2026.05		0.233	0.246	0.166	0.951	1.233	0.392	44.22
Mistral-7B2026.05		0.232	0.232	0.156	0.973	1.239	0.162	26.88
Mistral-7B2026.05		0.221	0.213	0.143	0.967	1.248	0.095	22.39
Mixtral-8x22B2026.05		0.218	0.217	0.145	1	1.25	0.371	42.66
Qwen2.5-7B2026.05		0.188	0.201	0.135	1.007	1.27	0.399	44.87
Mixtral-8x7B2026.05		0.174	0.172	0.115	1.011	1.285	0.339	40.09
Llama-8B2026.05		0.155	0.155	0.104	1.02	1.3	0.424	46.62
Mixtral-8x7B2026.05		0.093	0.084	0.057	1.047	1.345	0.277	35.69
Mistral-7B2026.05		0.082	0.082	0.055	1.046	1.35	0.332	39.49
Llama-8B2026.05		0.057	0.056	0.037	1.08	1.373	0.303	37.01
Olmo2-7B2026.05		0.002	-0.003	-0.002	1.105	1.412	0.356	41.07
Olmo2-7B2026.05		-0.034	-0.032	-0.021	1.121	1.438	0.331	39.12
Mistral-22B2026.05		-0.047	-0.053	-0.035	1.128	1.447	0.378	42.65
Mistral-22B2026.05		-0.072	-0.084	-0.056	1.141	1.464	0.37	42.14
Mistral-22B2026.05		-0.086	-0.094	-0.063	1.142	1.473	0.381	42.9
Olmo2-7B2026.05		-0.087	-0.103	-0.069	1.149	1.474	0.401	44.51