Best LLMs for Tool Calling — MiniMax
The best MiniMax model for tool calling is MiniMax M2.5, completing 95.3% of Tau²-Bench's multi-turn tool-use tasks. MiniMax M3 (88.9%) and MiniMax M2 (86.8%) round out the top three.
- 1
minimax-m2.5ReasoningToolsJSON33.7 intel · $0.150/M · 205K ctx95.3%τ²-Bench - 2minimax-m3ReasoningToolsJSON+144.4 intel · $0.300/M · 101 t/s88.9%τ²-Bench
- 3minimax-m2ReasoningToolsJSON28.3 intel · $0.255/M · 48 t/s86.8%τ²-Bench
- 4minimax-m2.1ReasoningToolsJSON31.4 intel · $0.300/M · 63 t/s85.4%τ²-Bench
- 5minimax-m2.7ReasoningToolsJSON38.1 intel · $0.270/M · 205K ctx84.8%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 MiniMax model is best at tool calling?
The best MiniMax model for tool calling is MiniMax M2.5, completing 95.3% of Tau²-Bench's multi-turn tool-use tasks. MiniMax M3 (88.9%) and MiniMax M2 (86.8%) round out the top three.
What's a good alternative to MiniMax M2.5?
MiniMax M3 (88.9%) is the closest alternative on this metric, followed by MiniMax M2 (86.8%). See the full ranking above for the tradeoffs.
How many MiniMax models are there?
modelgrep tracks 8 MiniMax models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by MiniMax M3. 5 of them qualify for this ranking.