List your company

Instruction Following on LIFEBench

57.6ScoreGPT-5.4-mini
44.0847.5951.154.61Jun 13, 2026

Evaluation results

MethodLinks
GPT-5.4-miniEvaluation Setting=non-reasoning2026.0657.6
Ling-2.6-flash2026.0657.2
GPT-OSS-120BEvaluation Setting=low2026.0649.4
Nemotron-3-Super 120B-A12BEvaluation Setting=non-reasoning2026.0644.6