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

MultiChallenge

multichallengeAgents & ToolsHigher is better

Complex, multi-constraint instruction following tasks.

Loading chart…

Loading leaderboard…

Benchmark Info

Current SOTA

Best Open Source

Median Score59.5%

DistributionLimited data

Score Distribution

P10

P50

P90

0100%

AgentBench

agentbench

IFEval

ifeval

Inverse IFEval

ifeval-inverse

IFBench

ifbench

Verified AdvancedIF

verified-advancedif

Terminal-Bench 2.0

terminal-bench