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

Vending-Bench 2

vending-bench-2Agents & ToolsHigher is better

Long-horizon business simulation benchmark (final account balance).

Loading chart…

Loading leaderboard…

Benchmark Info

Current SOTA

Best Open Source

GLM-54432.0USD

Median Score3635.0USD

DistributionBalanced

Score Distribution

P10

P50

P90

010000USD

AgentBench

agentbench

IFEval

ifeval

Inverse IFEval

ifeval-inverse

IFBench

ifbench

Verified AdvancedIF

verified-advancedif

MultiChallenge

multichallenge