Share your thoughts, 1 month free Claude Pro on usSee more

Coreference Resolution on SIMMC 2.1

59.98Precision

Qwen3

Updated 1mo ago

Evaluation Results

Method	Links
Qwen3 2026.04		59.98	45.21	51.55
Llama3.3 2026.04		58.73	61.37	60.02
DeepSeek-R1-Distill-Llama-8B 2026.04		53.5	43.92	48.24
Llama3.1 2026.04		52.16	59.23	55.47
Qwen2.5 2026.04		49.9	57.32	53.35
Mistral 2026.04		39.82	52.93	45.45
Llama3.3 2026.04		39.32	73.12	51.14
Qwen3 2026.04		39.13	59.15	47.1
Gemma 2026.04		37.86	43.24	40.37
Llama3.1 2026.04		30.34	68.39	42.03
Mistral 2026.04		29.14	62.65	39.77
Qwen3 2026.04		29.01	63.91	39.9
Qwen2.5 2026.04		28.84	70.05	40.86
Llama3.1 2026.04		27.74	63.03	38.53
Llama3.3 2026.04		26.61	80.1	39.95
Mistral 2026.04		25.7	66.62	37.09
DeepSeek-R1-Distill-Llama-8B 2026.04		25.31	67.17	36.77
Qwen2.5 2026.04		24.14	71.66	36.12
DeepSeek-R1-Distill-Llama-8B 2026.04		22.98	66.77	34.19
Gemma 2026.04		19.58	41.38	26.58
Gemma 2026.04		16.93	52.74	25.64
Random 2026.04		2.68	49.87	5.09