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.

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

About this benchmark

What Robust IF measures

Robust IF is a text benchmark that evaluates large language models on reasoning and instruction following tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.6, with the leader reaching 0.6.

Compare leaders on the best AI for reasoning and best AI for instruction following leaderboards.

MicrosoftMAI-Code-1-Flash leads with 61.2%.

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
Notice missing or incorrect data?

FAQ

Common questions about Robust IF.

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 reasoning and instruction following. The benchmark evaluates text models.

How recent are the Robust IF leaderboard results?

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

More evaluations to explore

Related benchmarks in the same category

View all reasoning
GPQA

A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.

reasoning
223 models
MMLU-Pro

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.

reasoning
127 models
AIME 2025

All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

reasoning
113 models
MMLU

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

reasoning
100 models
SWE-Bench Verified

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

reasoning
99 models
Humanity's Last Exam

Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

reasoningmultimodal
82 models