List your company

Agentic Reasoning on FRAMES n=50 (full)

77.31AccuracyGPT-5
32.496444.130755.76567.3993Dec 7, 2025

Evaluation results

MethodLinks
GPT-5Web search=true, Trials per question=642025.1277.31—0.0880.496
Claude 4.5 HaikuWeb search=true, Trials per question=642025.1268.37—0.1440.655
Claude 4.5 SonnetWeb search=true, Trials per question=642025.1266.44—0.1560.689
GPT-4oWeb search=true, Trials per question=642025.1263.54—0.1740.735
Gemini 2.5 ProWeb search=false, Trials per question=642025.1262.34—0.1740.713
Deepseek-v3p1Web search=false, Trials per question=642025.1244.75—0.1570.663
GPT-4oWeb search=false, Trials per question=642025.1238.16—0.1710.712
Qwen3-235b-a22bWeb search=false, Trials per question=642025.1234.22—0.1690.617