# Agentic IF Index (Internal) — AI model rankings

Meta's internal measure of whether a model keeps following the instructions it was given while working as an agent — over a long run of tool calls, not just in a single reply. Higher is better.

1 tracked model have a published Agentic IF Index (Internal) score. Higher is better. Scores are as published at each model's release.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Muse Spark 1.3 | Meta | 57.8% | Lab | Sep 2 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/agentic-if-index
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.