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

Long-context Question Answering on HotpotQA In-Distribution

85.2Accuracy

QwenLong-L1-32B

Updated 4d ago

Evaluation Results

Method	Links
QwenLong-L1-32B 2025.09		85.2
Qwen2.5-1M-14B 2025.09		83.6
QwenLong-L1-32B 2025.09		83.6
ReMemR1 2025.09		82.8
ReMemR1 2025.09		82.3
ReMemR1 2025.09		82
Qwen3-8B 2025.09		81.3
ReMemR1 2025.09		81.1
ReMemR1 2025.09		80.8
ReMemR1 2025.09		80
R1-Distill-Qwen-14B 2025.09		79.7
ReMemR1 2025.09		79.7
Qwen3-8B 2025.09		78.9
ReMemR1 2025.09		78.9
Qwen2.5-1M-14B 2025.09		78.1
R1-Distill-Qwen-14B 2025.09		76.6
Qwen2.5-1M-14B 2025.09		76.6
Qwen3-4B 2025.09		75.8
Qwen2.5-1M-7B 2025.09		75.8
Qwen3-4B 2025.09		75
Qwen3-8B 2025.09		74.2
QwenLong-L1-32B 2025.09		74.2
ReMemR1 2025.09		74
Qwen2.5-1M-14B 2025.09		73.4
QwenLong-L1-32B 2025.09		73.4
Qwen3-8B 2025.09		71.9
Qwen2.5-1M-7B 2025.09		71.9
ReMemR1 2025.09		71.7
ReMemR1 2025.09		70.9
Qwen3-8B 2025.09		70.3
Qwen2.5-1M-14B 2025.09		70.3
Qwen3-4B 2025.09		69.5
Qwen2.5-1M-7B 2025.09		69.5
Qwen2.5-1M-7B 2025.09		68
Qwen2.5-1M-7B 2025.09		67.2
ReMemR1 2025.09		66.1
ReMemR1 2025.09		65.4
ReMemR1 2025.09		65.4
ReMemR1 2025.09		65
R1-Distill-Qwen-14B 2025.09		64.1
ReMemR1 2025.09		63.8
Qwen3-4B 2025.09		63.3
Qwen2.5-1M-14B 2025.09		60.9
Qwen3-4B 2025.09		60.2
R1-Distill-Qwen-14B 2025.09		57.8
QwenLong-L1-32B 2025.09		57.8
Qwen2.5-1M-7B 2025.09		54.7
QwenLong-L1-32B 2025.09		45.3
Qwen2.5-1M-14B 2025.09		42.2
R1-Distill-Qwen-7B 2025.09		40.6
R1-Distill-Qwen-14B 2025.09		40.6
QwenLong-L1-32B 2025.09		38.9
QwenLong-L1-32B 2025.09		38.3
Qwen3-8B 2025.09		33.6
R1-Distill-Qwen-14B 2025.09		33.6
R1-Distill-Qwen-14B 2025.09		31.3
R1-Distill-Qwen-7B 2025.09		25.8
Qwen3-8B 2025.09		23.4
Qwen2.5-1M-7B 2025.09		22.7
Qwen3-4B 2025.09		21.9
R1-Distill-Qwen-14B 2025.09		20.3
Qwen3-8B 2025.09		19.5
Qwen3-4B 2025.09		18.8
Qwen3-4B 2025.09		18.8
R1-Distill-Qwen-7B 2025.09		10.2
R1-Distill-Qwen-7B 2025.09		3.1
R1-Distill-Qwen-7B 2025.09		2.3
R1-Distill-Qwen-7B 2025.09		1.6
R1-Distill-Qwen-7B 2025.09		1.5
R1-Distill-Qwen-7B 2025.09		0.8
Qwen2.5-1M-7B 2025.09		0
Qwen2.5-1M-14B 2025.09		0