The AI arena is free today

Open Superagent
All benchmarks

Agentic IF Index (Internal)

Progress Over Time

Interactive timeline showing model performance evolution on Agentic IF Index (Internal)

State-of-the-art frontier
Open
Proprietary

Agentic IF Index (Internal) Leaderboard

1 models
ContextCostLicense
1
Meta
Muse Spark 1.3
Meta
—1.0M$0.10 / $0.20
Notice missing or incorrect data?
About this benchmark

What is Agentic IF Index (Internal)?

Meta's internal Agentic Instruction-Following Index aggregates evaluations of compliance with tool-use constraints, fine-grained rubrics, compound constraints, long policies, and instructions embedded in structured workflows.

Agentic IF Index (Internal) is a text benchmark evaluating models on instruction following, agents, and tool calling tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.6.

Compare leaders on the best AI for instruction following, best AI for agents and best AI for tool calling leaderboards.

Current leaders

Muse Spark 1.3 from Meta currently leads the Agentic IF Index (Internal) leaderboard with a score of 0.578 across 1 evaluated AI models.

1Muse Spark 1.3Meta57.8%

FAQ

Common questions about the Agentic IF Index (Internal) benchmark and leaderboard.

What is the Agentic IF Index (Internal) benchmark?

Meta's internal Agentic Instruction-Following Index aggregates evaluations of compliance with tool-use constraints, fine-grained rubrics, compound constraints, long policies, and instructions embedded in structured workflows.

What is the Agentic IF Index (Internal) leaderboard?

The Agentic IF Index (Internal) leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Muse Spark 1.3 by Meta leads with a score of 0.578. The average score across all models is 0.578.

What is the highest Agentic IF Index (Internal) score?

The highest Agentic IF Index (Internal) score is 0.578, achieved by Muse Spark 1.3 from Meta.

How many models are evaluated on Agentic IF Index (Internal)?

1 models have been evaluated on the Agentic IF Index (Internal) benchmark, with 0 verified results and 1 self-reported results.

What categories does Agentic IF Index (Internal) cover?

Agentic IF Index (Internal) is categorized under instruction following, agents, and tool calling. The benchmark evaluates text models.

Which model offers the best value on Agentic IF Index (Internal)?

Among models scoring within 10% of the leader, Muse Spark 1.3 from Meta is the cheapest, at $0.10 per million input tokens with a score of 0.578.

How recent are the Agentic IF Index (Internal) leaderboard results?

The Agentic IF Index (Internal) leaderboard was last updated in September 2026 and currently includes 1 evaluated models.
Agentic IF Index (Internal) Leaderboard