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

Pairwise Citation Prediction on SciJudgeBench (test)

87.9CS Pairwise Accuracy

SciJudge-Qwen2.5-14B

Updated 1mo ago

Evaluation Results

Method	Links
SciJudge-Qwen2.5-14B 2026.03		87.9	78.7	74.4	84.9	80.6
SciJudge-Qwen2.5-32B 2026.03		85.4	77.9	82.2	89.9	83.7
SciJudge-Qwen3-30B 2026.03		83.5	78.7	78.7	82.3	80.6
SciJudge-Qwen2.5-7B 2026.03		83	68.8	71.5	87.4	76.9
Gemini-3.0-Pro-Preview 2026.03		81.1	73	72.6	76.5	75.7
GPT-5.2-Thinking 2026.03		79.1	68.8	69.4	73.1	72.7
GLM-5 2026.03		79.1	75.4	69.4	72.3	73.6
SciJudge-Qwen3-4B 2026.03		78.6	74.6	71.2	79.8	75.3
DeepSeek-V3.2-Thinking 2026.03		78.2	67.2	64.1	72.3	69.9
SciJudge-Qwen2.5-3B 2026.03		76.2	76.2	66.2	81.5	73.2
MiniMax-M2.5 2026.03		75.7	64.8	64.1	71.4	68.7
Qwen3-30B-A3B-Instruct 2026.03		73.8	70.5	59.4	65.5	66.3
SciJudge-Qwen2.5-1.5B 2026.03		72.3	73	69.4	77.3	72.1
Qwen2.5-32B-Instruct 2026.03		71.4	61.5	55.9	62.2	62.2
DeepSeek-V3.2 2026.03		67	68	57.3	62.2	62.6
Qwen3-4B-Instruct 2026.03		66.5	65.6	54.8	57.1	60.3
Qwen2.5-14B-Instruct 2026.03		64.1	63.9	54.5	56.3	59.1
Qwen2.5-7B-Instruct 2026.03		57.3	37.7	37	51.3	45.2
SciJudge-Llama3.1-8B 2026.03		56.8	59.8	55.2	60.5	57.3
Llama3.1-8B-Instruct 2026.03		34.5	44.3	35.9	35.3	36.8
Qwen2.5-3B-Instruct 2026.03		16.5	36.9	23.8	21	23.5
Qwen2.5-1.5B-Instruct 2026.03		6.3	10.7	6	6.7	7