List your company

Database Querying Agent Task on DB

70.1Success RateClaude-Sonnet-4
23.71635.75847.859.842Jul 8, 2026

Evaluation results

MethodLinks
Claude-Sonnet-4Category=API LLMs2026.0770.1
Claude-Sonnet-4 ThinkingCategory=API LLMs, Variant=Thinking2026.0768.4
o4-miniCategory=API LLMs2026.0763.4
GPT-5Category=API LLMs2026.0763.2
DCPOCategory=RL Training2026.0761
EPPOCategory=RL Training2026.0760.5
DeepSeek-R1Category=Open LLMs2026.0760.4
DeepSeek-V3Category=Open LLMs2026.0758.4
BAPOCategory=RL Training2026.0758.3
o3-miniCategory=API LLMs2026.0756.5
AgentRLCategory=RL Training2026.0756.3
Qwen2.5-32B-InstructCategory=Open LLMs, Parameters=32B, Variant=Instruct2026.0755.8
Qwen2.5-14B-InstructCategory=Open LLMs, Parameters=14B, Variant=Instruct2026.0748.4
AgentLM-70BCategory=Open LLMs, Parameters=70B2026.0737.7
AgentLM-13BCategory=Open LLMs, Parameters=13B2026.0733.7
Hephaestus-8B-BaseCategory=Open LLMs, Parameters=8B, Variant=Base2026.0732.3
AgentLM-7BCategory=Open LLMs, Parameters=7B2026.0730.6
Hephaestus-8B-IFTCategory=Open LLMs, Parameters=8B, Variant=IFT2026.0729.7
Qwen2.5-3B-InstructCategory=Open LLMs, Parameters=3B, Variant=Instruct2026.0725.5