List your company

Compositional Multi-hop QA on Bamboogle (Success Rate)

77.6Success RateLlama 3.1 405B
27.6840.6453.666.56Dec 22, 2025

Evaluation results

MethodLinks
Llama 3.1 405BScale group=Large Scale Models (> 10B), Model Size=405B2025.1277.6
Llama 3.1 70BScale group=Large Scale Models (> 10B), Model Size=70B2025.1276.8
Qwen 3 14BScale group=Large Scale Models (> 10B), Model Size=14B2025.1276
GenEnvScale group=7B Models, Model Size=7B2025.1276
Qwen 3 32BScale group=Large Scale Models (> 10B), Model Size=32B2025.1271.2
Qwen 2.5 72BScale group=Large Scale Models (> 10B), Model Size=72B2025.1269.6
ReSearchScale group=7B Models, Model Size=7B2025.1268
Qwen 2.5 7BScale group=7B Models, Model Size=7B2025.1268
SearchR1Scale group=7B Models, Model Size=7B2025.1267.2
ToRLScale group=7B Models, Model Size=7B2025.1234.4
GPT-OSS 20BScale group=Large Scale Models (> 10B), Model Size=20B2025.1233.6
GPT-OSS 120BScale group=Large Scale Models (> 10B), Model Size=120B2025.1229.6