List your company

Reasoning on BBH, GPQA, and MuSR Suite

83.4BBHQwen3-14B
42.94453.44763.9574.453Jan 14, 2026

Evaluation results

MethodLinks
Qwen3-14BParameters=14B2026.0183.449.857.763.6
Qwen3-4BParameters=4B2026.017939.858.559.1
Mi:dm 2.0 Base-instType=Instruction-tuned2026.0177.733.551.954.4
Llama-3.1-8B-instParameters=8B, Type=Instruction-tuned2026.0160.321.650.344.1
Exaone-3.5-7.8B-instParameters=7.8B, Type=Instruction-tuned2026.0150.133.151.244.8
Exaone-3.5-2.4B-instParameters=2.4B, Type=Instruction-tuned2026.0146.428.149.741.4
Mi:dm 2.0 Mini-instType=Instruction-tuned2026.0144.526.651.740.9