2 models
Ranked by τ3 Banking
Reasoning Tools Open weights 36.1

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

reflection/beam-1.0-501b-a23b 2026-10-05 1.04858M context $0.24/M input $0.98/M output
9 providers
Reasoning Tools JSON 20.6

Quality-first multi-agent model for hard research, analysis, and competitions

sakana/fugu-ultra 2026-06-15 1M context $5/M input $30/M output
14 providers