Skip to main content

Best Tool Use & Function Calling Models in 2026

This reporting page focuses on structured output, tool routing, function calling, and MCP-style task completion. It is narrower than the general agentic leaderboard and is better aligned to developers choosing models for tool-heavy applications.

This page ranks models using only sourced tool-use benchmarks in the reporting family.

Bottom line: Tool-use quality determines whether your AI agent can actually call APIs, use MCP servers, and route structured requests. Not all "agentic" models are equally good at it.

According to BenchLM.ai, GLM-5.1 leads this ranking with a score of 77.5, followed by Qwen3.7 Max (74.4) and GPT-5.4 (69.3). There is a significant gap between the leading models and the rest of the field.

The best open-weight option is GLM-5.1 (ranked #1 with a score of 77.5). Open-weight models are highly competitive in this category — self-hosting is a viable alternative to proprietary APIs.

This ranking is based on provisional overall weighted scores across BenchLM.ai's scoring formula tracked by BenchLM.ai. For detailed model profiles, click any model name below. To compare two specific models head-to-head, use the "vs #" links.

How to choose

Full Rankings (11 models)

GLM-5.1
Z.AI·Open Weight·203K

77.5

sourced avg

Qwen3.7 Max
Alibaba·Proprietary·1M

74.4

sourced avg

GPT-5.4
OpenAI·Proprietary·1.05M

69.3

sourced avg

4
Kimi K2.6
Moonshot AI·Open Weight·256K

66.6

sourced avg

5
Qwen3.6 Plus
Alibaba·Proprietary·1M

63.2

sourced avg

6
MiniMax M2.7
MiniMax·Open Weight·200K

62.9

sourced avg

7
Qwen3.6-35B-A3B
Alibaba·Open Weight·262K

60.1

sourced avg

8
Qwen3.5 397B
Alibaba·Open Weight·128K

59.2

sourced avg

9
Claude Opus 4.5
Anthropic·Proprietary·200K

58.7

sourced avg

10
GLM-5
Z.AI·Open Weight·200K

58.3

sourced avg

11
Kimi K2.5
Moonshot AI·Open Weight·256K

55.2

sourced avg

These rankings update weekly

Get notified when models move. One email a week with what changed and why.

Free. No spam. Unsubscribe anytime.

Key Takeaways

The top model on this sourced reporting-family slice is GLM-5.1 by Z.AI with an average of 77.5.

The best open-weight model is GLM-5.1 at position #1.

11 models are listed with sourced benchmark coverage in this reporting family.

Score in Context

What these scores mean

This ranking averages sourced tool-use benchmarks. It is narrower than the agentic category and focuses specifically on function calling and structured tool execution.

Known limitations

Tool-use benchmarks test specific function-calling patterns. Real-world tool use also depends on prompt engineering, retry logic, and error handling that benchmarks cannot capture.

Last updated: May 22, 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.