Beta version: *Information might not be fully accurate. Please report any discrepancies.

IFEval

ifevalAgents & ToolsHigher is better

Instruction Following Evaluation for Large Language Models. Measures ability to follow strict formatting and constraint requirements.

Loading chart…

Loading leaderboard…

Benchmark Info

Current SOTA

Best Open Source

Median Score92.6%

DistributionLimited data

Score Distribution

P10

P50

P90

0100%

AgentBench

agentbench

Inverse IFEval

ifeval-inverse

IFBench

ifbench

Verified AdvancedIF

verified-advancedif

MultiChallenge

multichallenge

Terminal-Bench 2.0

terminal-bench