1stTop pick
Researched 10d agoClaude Sonnet 4.6
- τ-bench
- 87.5%
- Output (from)
- $15.00 / 1M
Best LLMs for Function Calling (2026)
Last refreshed 2026-05-18. Next refresh: weekly.
Top AI models for agentic workflows, tool use, and API integration. Compare models with native function calling support and structured outputs.
Top three picks
Opinionated short stack for this category — scroll for the full leaderboard, pricing, and compare links.
How we rank
Tool-use leaders rank on BFCL first; when Berkeley coverage lags new SKUs, we fall back to τ-bench so fresh agentic models still surface.
- Eligibility — Models with `function_calling` or `tool_use` enabled in seed metadata.
- Primary ranking — BFCL score if present, otherwise τ-bench, then newer release.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). When headline scores tie within ±0.5 pt (±10 Elo on Chatbot Arena), we pick the canonical SKU by lowest tracked input price, then GA over preview or limited access, then newest `release`. A folded sibling within the benchmark noise band can show a "Tied within margin" chip on that score cell.
- Pricing — Lowest tracked input(output) for API routes.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Claude Mythos Preview PreviewReasoningVisionTools Signal used: τ-bench 89.2% | — | — | |
| 2 | Claude Sonnet 4.6 ReasoningVisionTools Signal used: τ-bench 87.5% | $3.00 | $15.00 | |
| 3 | GLM-5 ReasoningTools Signal used: τ-bench 82.1% | $0.60 | $2.08 | |
| 4 | GPT-5.4 ReasoningTools Signal used: τ-bench 78.3% | $2.50 | $15.00 | |
| 5 | GPT-5.3-Codex ReasoningVisionTools Signal used: τ-bench 77.8% | $1.75 | $14.00 | |
| 6 | Claude Opus 4.5 ReasoningVisionTools Signal used: BFCL 77.47% | $5.00 | $25.00 | |
| 7 | Qwen3-Max VisionTools Signal used: τ-bench 76.8% | $0.78 | $3.90 | |
| 8 | Gemini 3.1 Pro Preview PreviewVisionTools Signal used: τ-bench 76.5% | $2.00 | $12.00 | |
| 9 | GPT-5.2 ReasoningVisionTools Signal used: τ-bench 75.1% | $1.75 | $14.00 | |
| 10 | Claude Sonnet 4.5 ReasoningVisionTools Signal used: BFCL 73.24% | $3.00 | $15.00 | |
| 11 | Qwen3.5-397B-A17B ReasoningTools Signal used: BFCL 72.9% | $0.39 | $2.34 | |
| 12 | Gemini 3 Pro VisionTools Signal used: BFCL 72.51% | $1.25 | $5.00 | |
| 13 | Gemini 3 Flash PreviewVisionTools Signal used: τ-bench 71.5% | $0.50 | $3.00 | |
| 14 | Claude Haiku 4.5 VisionTools Signal used: BFCL 68.7% | $0.80 | $4.00 | |
| 15 | Kimi K2.5 Tools Signal used: BFCL 68.3% | $0.44 | $2.00 | |
| 16 | Gemini 2.5 Flash VisionTools Signal used: BFCL 56.24% | $0.30 | $2.50 | |
| 17 | GPT-5 Mini ReasoningVisionTools Signal used: BFCL 55.46% | $0.25 | $2.00 | |
| 18 | GPT-4.1 VisionTools Signal used: BFCL 53.96% | $2.00 | $8.00 | |
| 19 | GPT-4.1 Mini VisionTools Signal used: BFCL 50.45% | $0.40 | $1.60 | |
| 20 | Mistral Large 2 VisionTools Signal used: BFCL 38.37% | $0.48 | $1.50 |
Honorable mentions
Next seats in this ranking. Lines below are from each model's stored description in LLMReference seed data—spot-check the model page before relying on a capability claim.
Most capable agentic coding model from OpenAI. Optimized for long-horizon, agentic coding tasks in the Codex CLI and API. Note: GPT-5.3-Codex-Spark is a distinct ChatGPT Pro research preview (not API-accessible).
77.8%
τ-bench
Claude Opus 4.5 available on AWS Bedrock
77.47%
BFCL
Alibaba's Qwen3-Max, flagship model with improved multilingual and reasoning capabilities.
76.8%
τ-bench
Compare Top Picks
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest AI Agents & Agentic ModelsBest LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLMs for Reasoning & MathBest Small Language Models (SLMs)Cheapest LLM APIs You Can Call Right NowBest Long Context LLMsBest Mainstream LLM APIs, RankedBest LLMs for EnterpriseBest Free LLMs You Can Use Right NowBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support