All benchmarks

Robust IF

Progress Over Time

Interactive timeline showing model performance evolution on Robust IF

State-of-the-art frontier
Open
Proprietary

Robust IF Leaderboard

1 models
ContextCostLicense
1
Microsoft
MAI-Code-1-Flash
Microsoft
———
Notice missing or incorrect data?
About this benchmark

What is Robust IF?

Robust IF evaluates instruction-following robustness on diverse, hard prompts, measuring whether a model reliably adheres to constraints across challenging single-turn and multi-turn scenarios.

Robust IF is a text benchmark evaluating models on instruction following and reasoning 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 and best AI for reasoning leaderboards.

Current leaders

MAI-Code-1-Flash from Microsoft currently leads the Robust IF leaderboard with a score of 0.612 across 1 evaluated AI models.

1MAI-Code-1-FlashMicrosoft61.2%

FAQ

Common questions about the Robust IF benchmark and leaderboard.

What is the Robust IF benchmark?

Robust IF evaluates instruction-following robustness on diverse, hard prompts, measuring whether a model reliably adheres to constraints across challenging single-turn and multi-turn scenarios.

What is the Robust IF leaderboard?

The Robust IF leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, MAI-Code-1-Flash by Microsoft leads with a score of 0.612. The average score across all models is 0.612.

What is the highest Robust IF score?

The highest Robust IF score is 0.612, achieved by MAI-Code-1-Flash from Microsoft.

How many models are evaluated on Robust IF?

1 models have been evaluated on the Robust IF benchmark, with 0 verified results and 1 self-reported results.

What categories does Robust IF cover?

Robust IF is categorized under instruction following and reasoning. The benchmark evaluates text models.

How recent are the Robust IF leaderboard results?

The Robust IF leaderboard was last updated in July 2026 and currently includes 1 evaluated models.