List your company

Commonsense Reasoning on XCSQA

64.6CLCall ScoreQwen2.5-14B
2.218.434.650.8Mar 4, 2026

Evaluation results

MethodLinks
Qwen2.5-14BModel=Qwen2.5-14B2026.0364.68756.9
Aya-Expanse-8BModel=Aya-Expanse-8B2026.0362.67854.4
Qwen3-14BModel=Qwen3-14B2026.0361.977.654
Llama3.1-8BModel=Llama3.1-8B2026.0360.267.547.7
Gemma3-12B-ptModel=Gemma3-12B-pt2026.0358.36647.2
DCOBase Model=Llama3.1-8B2026.039.10.21.3
DCOBase Model=Qwen3-14B2026.037.11.13.8
DCOBase Model=Qwen2.5-14B2026.036.8-2.54.7
DCOBase Model=Aya-Expanse-8B2026.036.40.63.7
DCOBase Model=Gemma3-12B-pt2026.034.60.13.6