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

Long-Context Reasoning on BrowsCompLong

88.07Accuracy

Gemini-3.0-pro

Updated 25d ago

Evaluation Results

Method	Links
Gemini-3.0-pro 2026.03		88.07
Deepseek-R1-Distill-Qwen-14B + TableLong 2026.03		74.31
Deepseek-R1-Distill-Qwen-32B + TableLong 2026.03		74.31
Qwen-Long-L1 2026.03		69.93
Qwen3-32B + TableLong 2026.03		65.44
Deepseek-R1-Distill-Qwen-32B 2026.03		64.22
Qwen2.5-32B-Instruct + TableLong 2026.03		60.55
Qwen3-32B 2026.03		59.33
Deepseek-v3.1 2026.03		56.27
Qwen2.5-32B-Instruct 2026.03		52.56
Deepseek-R1-Distill-Qwen-14B 2026.03		51.38