List your company

Citation Validity Judgment on Citation Validity Ground Truth Archival Analysis 1.0 (test)

62Valid RecallSeed
1023.53750.5Feb 6, 2026

Evaluation results

MethodLinks
Seed2026.02623247
Gemini2026.02402432
Hunyuan2026.02385848
Llama-42026.02383235
GLM-4.52026.02382833
DeepSeek2026.02323835
Kimi-K22026.02285240
Grok-42026.02283632
Qwen-32026.02264234
Phi-42026.02245841
Claude-42026.02243027
GPT-52026.02165636
ERNIE2026.021210056