List your company

Knowledge Base Question Answering on GrailQA (dev)

89.5Overall F1GAPD
40.30853.07965.8578.621Dec 10, 2025Jan 7, 2026Feb 4, 2026Mar 4, 2026Apr 1, 2026Apr 29, 2026May 28, 2026

Evaluation results

MethodLinks
GAPDLLM=Llama-3.1-8B, Method Category=Fine-tune-based Methods2026.0589.5——————87.8
GAPDLLM=Llama-3.1-8B, Method Category=Fine-tune-based Methods2026.0588.7——————87.8
KBQA-R1LLM=Llama-3.1-8B, Method Category=Fine-tune-based Methods2026.0586.1——————83.9
KBQA-R1LLM=Llama-3.1-8B, Method Category=Fine-tune-based Methods2026.0585.2——————83.6
KnowCoder-A1LLM=Qwen2.5-Coder-7B, Method Category=Fine-tune-based Methods2026.0584.1———————
TIARALLM=T5-large, Method Type=Fine-tune-based Methods2025.1281.988.491.266.474.873.380.775.3
KBQA-R1 HarnessLLM=Claude 4.6 Sonnet, Method Category=Prompting Methods2026.0581.9——————79.1
TIARALLM=T5-large, Method Category=Fine-tune-based Methods2026.0581.9——————75.3
DecAFLLM=T5-large, Method Type=Fine-tune-based Methods2025.1281.488.792.471.579.865.977.372.5
DecAFLLM=T5-large, Method Category=Fine-tune-based Methods2026.0581.4——————72.5
TIARALLM=T5-large, Method Category=Fine-tune-based Methods2026.0580.7——————73.3
KnowCoder-A1LLM=Qwen2.5-Coder-7B, Method Category=Fine-tune-based Methods2026.0580.5———————
KBQA-R1 HarnessLLM=gpt-5.3-codex, Method Category=Prompting Methods2026.0579.6——————77.4
KBQA-o1LLM=Llama-3.1-8B, Method Category=Fine-tune-based Methods2026.0578.5——————71.9
KBQA-R1 HarnessLLM=Kimi-K2.5, Method Category=Prompting Methods2026.0578——————73.9
DecAFLLM=T5-large, Method Category=Fine-tune-based Methods2026.0577.3——————65.9
RnG-KBQALLM=T5-large, Method Type=Fine-tune-based Methods2025.1276.986.78961.768.968.874.769.5
RnG-KBQALLM=T5-large, Method Category=Fine-tune-based Methods2026.0576.9——————69.5
KBQA-R1 HarnessLLM=Claude 4.6 Sonnet, Method Category=Prompting Methods2026.0576.3——————72
KBQA-o1LLM=Llama-3.1-8B, Method Category=Fine-tune-based Methods2026.0576.1——————68.1
KBQA-R1 HarnessLLM=GLM-5, Method Category=Prompting Methods2026.0575.5——————68.7
RnG-KBQALLM=T5-large, Method Category=Fine-tune-based Methods2026.0574.7——————68.8
KBQA-R1 HarnessLLM=Kimi-K2.5, Method Category=Prompting Methods2026.0573.9——————68.5
KBQA-R1 HarnessLLM=gpt-5.3-codex, Method Category=Prompting Methods2026.0573.5——————68.6
KBQA-R1 HarnessLLM=GLM-5, Method Category=Prompting Methods2026.0570.2——————60
ARG-KBQALLM=GPT-3.5-turbo, Method Category=Prompting Methods2026.0552.1——————46.6
ARG-KBQALLM=GPT-3.5-turbo, Method Type=Prompting Methods2025.1248.546.651.536.441.846.652.143.8
ARG-KBQALLM=GPT-3.5-turbo, Method Category=Prompting Methods2026.0548.5——————43.8
KB-CoderLLM=GPT-3.5-turbo, Method Category=Prompting Methods2026.0547.3——————42.2
KB-CoderLLM=GPT-3.5-turbo, Method Type=Prompting Methods2025.1244.940.645.534.538.642.247.340.1
KB-CoderLLM=GPT-3.5-turbo, Method Category=Prompting Methods2026.0544.9——————40.1
KB-BINDERLLM=Codex-davinci-002, Method Category=Prompting Methods2026.0544——————40.1
KB-BINDERLLM=Codex-davinci-002, Method Type=Prompting Methods2025.1242.24043.333.936.640.14438.7
KB-BINDERLLM=Codex-davinci-002, Method Category=Prompting Methods2026.0542.2——————38.7