List your company

Citation Prediction Task 1 on CiteRAG 1.0 (test)

7.6Recall@20Gemini-2.5-Pro
0.322.214.15.99Jan 21, 2026

Evaluation results

MethodLinks
Gemini-2.5-ProRAG=R=102026.017.69.734.625.214.418.8
CitationGenerator-30BSFT=Yes, RAG=R=102026.017.612.236.729.519.321.9
CitationGenerator-30BSFT=Yes, RAG=R=52026.017.211.333.827.318.320.4
GPT-5RAG=R=102026.017.19.932.424.813.619.3
Gemini-2.5-ProRAG=R=52026.016.98.732.923.513.417
GPT-5RAG=R=52026.016.59.330.623.112.418.1
Claude-3.7RAG=R=102026.016.58.13021.712.616.2
Claude-4-SonnetRAG=R=102026.016.4829.621.312.215.7
GPT-5RAG=None2026.016.1926.321.211.517.6
Kimi-K2RAG=R=102026.016.17.527.319.511.714.6
Deepseek-v3RAG=R=102026.016727.819.311.113.7
Claude-3.7RAG=R=52026.015.77.127.519.61114
GPT-o3RAG=R=102026.015.56.426.418.410.412.6
Gemini-2.5-ProRAG=None2026.015.56.927.219.510.813.8
Claude-3.5RAG=R=102026.015.46.226.41810.312.1
Claude-4-SonnetRAG=R=52026.015.46.826.819.31013.6
Kimi-K2RAG=R=52026.015.26.424.517.51012.6
Deepseek-v3RAG=R=52026.0155.824.817.19.611.4
Qwen3-Coder-480BRAG=R=102026.014.95.421.614.79.510.6
Gemini-2.0-FlashRAG=R=102026.014.85.82316.29.211.4
GPT-o3RAG=R=52026.014.45.12315.78.610.1
Claude-3.5RAG=R=52026.014.452315.78.49.8
GPT-oss-120BRAG=R=102026.014.34.621.914.48.39
CitationGenerator-30BSFT=Yes, RAG=None2026.014.36.922.519.811.313
Claude-3.7RAG=None2026.014.25.419.714.48.110.7
Grok-3RAG=R=102026.0144.219.212.27.77.9
Claude-4-SonnetRAG=None2026.013.85.118.713.97.610.3
Qwen3-Coder-480BRAG=R=52026.013.74.217.712.17.28.3
Kimi-K2RAG=None2026.013.64.617.712.77.19.1
Gemini-2.0-FlashRAG=R=52026.013.54.31812.76.88.6
CitationGenerator-30BSFT=No, RAG=R=102026.013.13.515.3105.96.3
GPT-o3RAG=None2026.012.93.416.611.35.96.8
Claude-3.5RAG=None2026.012.83.4149.85.56.7
Deepseek-v3RAG=None2026.012.83.314.39.95.56.7
GPT-oss-120BRAG=R=52026.012.73.115.510.35.46
CitationGenerator-4BSFT=Yes, RAG=R=102026.012.73.912.99.85.37.4
Grok-3RAG=R=52026.012.42.513.48.74.74.9
Gemini-2.0-FlashRAG=None2026.012.3311.58.44.56
CitationGenerator-4BSFT=Yes, RAG=R=52026.012.33.410.78.44.26.5
CitationGenerator-4BSFT=No, RAG=R=102026.012.12.312.27.84.14.5
CitationGenerator-30BSFT=No, RAG=R=52026.012.12.411.77.63.94.2
Qwen3-Coder-480BRAG=None2026.011.92.3107.13.74.7
Grok-3RAG=None2026.011.61.7963.13.4
GPT-oss-120BRAG=None2026.011.61.89.56.33.33.7
CitationGenerator-4BSFT=Yes, RAG=None2026.011.21.95.54.72.23.9
CitationGenerator-4BSFT=No, RAG=R=52026.011.11.25.63.42.42.7
CitationGenerator-30BSFT=No, RAG=None2026.0111.15.73.822.3
CitationGenerator-4BSFT=No, RAG=None2026.010.60.72.92.11.31.7