AgentLM-7B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1269 ± 52, rank #9074 of 10916 rated models, from 8 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Portuguese LLM - FaQuAD NLI56.54Macro F1 (%)39
AgentBench FC42.7Avg Success Rate (%)37.5
Open Portuguese LLM - OAB Exams34.72Accuracy (%)31.5
Open Portuguese LLM - BLUEX36.72Accuracy (%)30.4
Open Portuguese LLM - ENEM38.07Accuracy (%)29.2
Open Portuguese LLM - ASSIN2 RTE70.84Macro F1 (%)25.3
T-Eval41.4Overall Score (%)15
WebArena0.74Success Rate (%)4.3

Interactive version: theaggregate.ai/model?slug=agentlm-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.