List your company

General Reasoning on TriviaQA

73.33AccuracyCOSE
15.786830.725945.66560.6041May 27, 2026

Evaluation results

MethodLinks
COSEModel=Qwen3-4B2026.0573.33
COSEModel=Llama-3.2-3B-Instruct2026.0571.86
COSEModel=Qwen3-0.6B2026.0571.55
MAEModel=Qwen3-4B2026.0568.9
AZRModel=Qwen3-4B2026.0568.4
R-ZeroModel=Qwen3-4B2026.0568.2
BaseModel=Qwen3-4B2026.0566
MAEModel=Qwen2.5-3B-Instruct2026.0560.13
R-ZeroModel=Llama-3.2-3B-Instruct2026.0559.53
MAEModel=Llama-3.2-3B-Instruct2026.0559
AZRModel=Llama-3.2-3B-Instruct2026.0558.23
R-ZeroModel=Qwen2.5-3B-Instruct2026.0558.2
BaseModel=Llama-3.2-3B-Instruct2026.0558
AZRModel=Qwen2.5-3B-Instruct2026.0556.67
COSEModel=Qwen2.5-3B-Instruct2026.0553
BaseModel=Qwen2.5-3B-Instruct2026.0551.6
MAEModel=Qwen3-0.6B2026.0525.8
R-ZeroModel=Qwen3-0.6B2026.0524.6
AZRModel=Qwen3-0.6B2026.0521.75
BaseModel=Qwen3-0.6B2026.0518