Thinking Machines' ReViSQL-K2.6 scores 91.37% on cleaned SQL benchmark
ReViSQL-K2.6 reached 88.55% with greedy decoding and 91.37% with 16-sample self-consistency on the corrected Arcwise-Plat-SQL benchmark.
By RuntimeWire Staff · Published
Primary source: Thinking Machines Newsroom
Why it matters
ReViSQL supports Murati's argument that specialized training can beat bigger models and intricate agent workflows, but it also exposes the bill: expert data cleanup and carefully designed rewards remain essential.
Mira Murati (@miramurati)'s Thinking Machines Lab and four academic researchers trained a single model to outperform elaborate text-to-SQL agent pipelines, after finding that errors riddled the benchmark data used to teach and judge those systems.…