modelgrep

Best LLMs for Tool Calling — inclusionAI

Match · Updated August 2026

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.

92.4%τ²-Bench
30.6Intelligence
60 t/sSpeed
$0.075Input /M
262KContext
  1. 1I
    ring-2.6-1t
    ReasoningToolsJSON30.6 intel · $0.075/M · 60 t/s
    92.4%
    τ²-Bench
  2. 2I
    ling-2.6-1t
    ToolsJSON26.1 intel · $0.075/M · 36 t/s
    89.8%
    τ²-Bench
  3. 3I
    ling-2.6-flash
    ToolsJSON14.1 intel · $0.010/M · 62 t/s
    86.0%
    τ²-Bench

How this is ranked

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.

Frequently asked

Which inclusionAI model is best at tool calling?

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.

What's a good alternative to Ring-2.6-1T?

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.

How many inclusionAI models are there?

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.

More inclusionAI rankings

All rankings