glm-4-9B-chat-hf: benchmark results

Zhipu's GLM-4-9B-Chat release for the native Transformers GlmForCausalLM implementation, supporting 128K context; distinct from the base and 1M-context releases. Provider: Zhipu. Access: Open.

Aggregate Rating 1468 ± 44, rank #3133 of 10556 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Portuguese LLM - ASSIN2 RTE92.72Macro F1 (%)82.5
FaithJudge - RAGTruth Summarization9.33Hallucination rate (%) on 150 RAGTruth summaries79.7
Open LLM Leaderboard - IFEval65.13Score77.5
Open Portuguese LLM - FaQuAD NLI75.71Macro F1 (%)74.3
FaithJudge - FaithBench Summarization38.89Hallucination rate (%) on 72 FaithBench summaries68.9
Open Portuguese LLM - BLUEX56.05Accuracy (%)65.1
Open Portuguese LLM - OAB Exams46.24Accuracy (%)63.3
Open LLM Leaderboard - GPQA30.29Score59.3
Open Portuguese LLM - ENEM62.07Accuracy (%)50.9
Open LLM Leaderboard - MATH Level 58.46Score42.4
FaithJudge25.44Hallucination rate (%), pooled over 511 RAG responses (Faith32.4
Open LLM Leaderboard - BBH44.32Score32.4

Interactive version: theaggregate.ai/model?slug=glm-4-9b-chat-hf · How It Works · Data refreshed daily, snapshot 2026-11-17.