Building AI agents? These 216 models support function calling and are ranked by their agentic capability coverage — tool use, reasoning, JSON output, streaming, vision, and web search.
| # | Model | Score |
|---|---|---|
| 1 | o1OpenAI | 65 |
| 2 | Nemotron Nano 12B 2 VL (free)NVIDIA | 64 |
| 3 | Nova 2 LiteAmazon | 61 |
| 4 | Gemma 3 27B (free)Google | 56 |
| 5 | Gemini 2.0 Flash LiteGoogle | 55 |
| 6 | Qwen Plus 0728 (thinking)Alibaba | 55 |
| 7 | Gemini 2.0 FlashGoogle | 54 |
| 8 | MiniMax M2.5MiniMax | 54 |
| 9 | Trinity Large Preview (free)arcee-ai | 54 |
| 10 | Trinity Mini (free)arcee-ai | 54 |
| 11 | MiniMax M2MiniMax | 54 |
| 12 | Nemotron Nano 9B V2 (free)NVIDIA | 54 |
| 13 | Qwen3 VL 32B InstructAlibaba | 54 |
| 14 | Qwen3 VL 8B InstructAlibaba | 54 |
| 15 | Qwen3 VL 30B A3B InstructAlibaba | 54 |
| 16 | Qwen3 Max ThinkingAlibaba | 54 |
| 17 | MiMo-V2-FlashXiaomi | 54 |
| 18 | Trinity Miniarcee-ai | 53 |
| 19 | Tongyi DeepResearch 30B A3BAlibaba | 53 |
| 20 | DeepSeek V3.2DeepSeek | 53 |
The foundation of agentic AI. Models must be able to decide when and how to call external tools — APIs, databases, file systems, web browsers. Without this, agents can only produce text, not take action.
Agents need to produce structured, parseable output reliably. JSON mode ensures the model always returns valid JSON, preventing the parsing errors that break automated workflows.
Chain-of-thought reasoning helps agents plan multi-step sequences, recover from errors, and make better decisions about which tools to use. Critical for complex autonomous workflows.
Streaming lets you observe agent actions in real-time — see which tools it's calling, watch it reason through problems, and intervene early if it goes off track. Essential for interactive agent interfaces.
Vision-capable agents can process screenshots, analyze charts, read documents, and interact with visual interfaces. Required for browser automation, document processing, and GUI agents.
Built-in web search lets agents find current information without custom search tool integrations. Ideal for research agents, fact-checkers, and competitive analysis workflows.