What is the current top score on IFBench?

The top reported score is 82.9% by Grok 4.20 0309, across 327 models reporting (69 from frontier labs).

How can a model improve its IFBench score?

Tools linked to IFBench on Sophon include Ifbench (Fares), Ifbench (Prime Intellect), Ifbench (Shashwat23) - RL environments, datasets, and scaffolds that target this eval.

IFBench

Frontier

Instruction-following benchmark measuring adherence to multi-step constraints.

Open

Publisher: Allen Institute for AI
Published: Jun 2025
Canonical: github.com/allenai/IFBench

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores: AA

Attribution policy →

Top score 82.9% by Grok 4.20 0309 - 327 models reporting (69 frontier)

Score history

327

Top models

327

IFBenchBar chart with 21 bars. Highest value: Grok 4.20 0309 at 82.9.

21 models

Related tools

View all

Implementations, trainers, datasets and scaffolds linked to this eval.

Ifbench (Fares)

IFBench evaluation environment

ImplementationRL EnvIfbench

Ifbench (Prime Intellect)

Prime Intellect

IFBench evaluation environment

ImplementationRL EnvV1

Ifbench (Shashwat23)

IFBench evaluation environment for precise instruction following with verifiable constraints

ImplementationRL EnvInstruction FollowingVerificationConstraints

FAQ

What is IFBench?: Instruction-following benchmark measuring adherence to multi-step constraints.
What is the current top score on IFBench?: The top reported score is 82.9% by Grok 4.20 0309, across 327 models reporting (69 from frontier labs).
How can a model improve its IFBench score?: Tools linked to IFBench on Sophon include Ifbench (Fares), Ifbench (Prime Intellect), Ifbench (Shashwat23) - RL environments, datasets, and scaffolds that target this eval.