AgentJudgeBench (Hard, With Ground Truth) - Llama-3.1-8B-Instruct Outputs: leaderboard

Metric: Judge alignment (%; agreement of the judge's per-metric verdicts (tool selection, parameter structure, call sequence, query coverage) with the programmatic reference on the hard (most ambiguous) rewrite of 3,808 BFCL-style tool-calling records over six workflow-DAG topologies; judged outputs from Llama-3.1-8B-Instruct at temperature 0; the judge sees the ground-truth tool calls). Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.

Top models

#ModelScore
1QwQ-32B84.1
2GPT-OSS-120B83.6
3GPT-OSS-20B81.2
4GPT-5.480.6
5Claude Sonnet 4.580.3
6Gemini 2.5 Pro (Preview 05-06)78.7

Interactive version: theaggregate.ai/benchmark?slug=agentjudgebench-hard-with-ground-truth-llama-3-1-8b-instruct-outputs · How It Works · Data refreshed daily, snapshot 2026-09-29.