The best inclusionAI model for tool calling is Ring-2.6-1T, completing 92.4% of Tau²-Bench's multi-turn tool-use tasks. Ling-2.6-1T (89.8%) and Ling-2.6-flash (86.0%) round out the top three.
AI models ranked by Tau²-Bench — multi-turn conversations where the model has to call the right tools, in the right order, against a real API to complete a customer task. This measures whether function calling actually works under pressure, which is a different question from whether a model supports the parameter at all.
The best inclusionAI model for tool calling is Ring-2.6-1T, completing 92.4% of Tau²-Bench's multi-turn tool-use tasks. Ling-2.6-1T (89.8%) and Ling-2.6-flash (86.0%) round out the top three.
Ling-2.6-1T (89.8%) is the closest alternative on this metric, followed by Ling-2.6-flash (86.0%). See the full ranking above for the tradeoffs.
modelgrep tracks 4 inclusionAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Ring-2.6-1T. 3 of them qualify for this ranking.