{"benchmark_id":"nolima-64k","benchmark_name":"NoLiMa 64K","benchmark_description":"NoLiMa evaluated at a 65536-token context length. Tests latent associative reasoning in long contexts with minimal lexical overlap between questions and needles.","max_score":1.0,"categories":["long_context","reasoning"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"minicpm-sala","model_name":"MiniCPM-SALA","organization_name":"OpenBMB","organization_id":"openbmb","benchmark_score":0.4295,"normalized_score":0.4295,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-02-11","announcement_date":"2026-02-11","multimodal":false,"param_count":9477203968,"is_new":false}]}