List your company

Citation Prediction Task 2 on CiteRAG 1.0 (test)

27.3PACA@10CitationGenerator-30B
-0.1566.97214.121.228Jan 21, 2026

Evaluation results

MethodLinks
CitationGenerator-30BSFT=Yes, RAG=R=102026.0127.330.334.2
CitationGenerator-30BSFT=Yes, RAG=R=52026.0126.829.131.8
CitationGenerator-30BSFT=Yes, RAG=None2026.0114.916.519.1
Gemini-2.5-ProRAG=R=102026.0112.71720.1
CitationGenerator-4BSFT=Yes, RAG=R=102026.0111.914.816.4
Qwen3-Coder-480BRAG=R=102026.0111.31416.1
Deepseek-v3RAG=R=102026.0110.813.515.8
Gemini-2.0-FlashRAG=R=102026.0110.713.817.1
Deepseek-v3RAG=R=52026.0110.313.115.3
Grok-3RAG=R=102026.0110.112.213.3
Qwen3-Coder-480BRAG=R=52026.0110.112.113.8
Gemini-2.5-ProRAG=R=52026.019.912.915.5
GPT-5RAG=R=102026.019.812.114.3
Kimi-K2RAG=R=102026.019.812.314.3
CitationGenerator-30BSFT=No, RAG=R=102026.019.611.412.4
GPT-oss-120BRAG=R=102026.018.710.812.2
CitationGenerator-4BSFT=Yes, RAG=R=52026.018.79.610.1
GPT-5RAG=R=52026.018.610.913.1
Kimi-K2RAG=R=52026.018.510.412
Claude-3.7RAG=R=102026.018.210.512.5
Gemini-2.0-FlashRAG=R=52026.018.210.513.4
Grok-3RAG=R=52026.018.29.29.8
Claude-4-SonnetRAG=R=102026.01810.112.2
Claude-4-SonnetRAG=R=52026.017.69.711.5
CitationGenerator-30BSFT=No, RAG=R=52026.017.68.48.9
Gemini-2.5-ProRAG=None2026.017.19.211.3
GPT-oss-120BRAG=R=52026.016.98.29
Claude-3.7RAG=R=52026.016.38.19.9
CitationGenerator-4BSFT=No, RAG=R=102026.016.37.89.2
Claude-3.5RAG=R=102026.015.76.97.8
GPT-5RAG=None2026.015.36.98.1
CitationGenerator-4BSFT=No, RAG=R=52026.015.16.47.4
Kimi-K2RAG=None2026.014.86.68
Deepseek-v3RAG=None2026.014.86.37.3
Claude-3.5RAG=R=52026.014.65.66.4
Claude-4-SonnetRAG=None2026.014.66.48
GPT-o3RAG=R=102026.014.55.86.8
Qwen3-Coder-480BRAG=None2026.014.25.36.5
Claude-3.7RAG=None2026.0145.47.1
GPT-o3RAG=R=52026.013.94.96
GPT-o3RAG=None2026.0133.64.1
Grok-3RAG=None2026.0134.35.4
Gemini-2.0-FlashRAG=None2026.012.83.95.1
Claude-3.5RAG=None2026.012.42.93.4
GPT-oss-120BRAG=None2026.012.42.83.1
CitationGenerator-4BSFT=Yes, RAG=None2026.011.72.94.2
CitationGenerator-30BSFT=No, RAG=None2026.011.41.61.7
CitationGenerator-4BSFT=No, RAG=None2026.010.911.2