Back to all LLMs

GLM 4.6

Native bilingual English/Chinese support for cross-lingual RAG without translation overhead. MIT license enables fine-tuning on proprietary knowledge bases with self-hosting via vLLM/SGLang. If you want to compare the best LLMs for your data, try Agentset.

Leaderboard Rank
#12
of 16
ELO Rating
1331
#12
Win Rate
28.5%
#12
Latency
33116ms
#15

Model Information

Provider
Zhipu AI
License
Open Source
Input Price per 1M
$0.40
Output Price per 1M
$1.75
Context Window
203K
Release Date
2025-09-30
Model Name
glm-4.6
Total Evaluations
1350

Performance Record

Wins385 (28.5%)
Losses809 (59.9%)
Ties156 (11.6%)
Wins
Losses
Ties

LLMs Are Just One Piece of RAG

Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no LLM orchestration to manage.

Trusted by teams building production RAG applications

5M+
Documents
1,500+
Teams
99.9%
Uptime

Performance Overview

ELO ratings by dataset

GLM 4.6's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

GLM 4.6 - ELO by Dataset

Detailed Metrics

Dataset breakdown

Performance metrics across different benchmark datasets, including accuracy and latency percentiles.

MSMARCO

ELO 144432.2% WR145W-255L-50T

Quality Metrics

Correctness
4.83
Faithfulness
4.80
Grounding
4.80
Relevance
4.93
Completeness
4.73
Overall
4.82

Latency Distribution

Mean
34694ms
Min
9198ms
Max
69527ms

SciFact

ELO 133718.0% WR81W-285L-84T

Quality Metrics

Correctness
4.60
Faithfulness
4.83
Grounding
4.83
Relevance
4.87
Completeness
4.53
Overall
4.73

Latency Distribution

Mean
27880ms
Min
3248ms
Max
68513ms

PG

ELO 121235.3% WR159W-269L-22T

Quality Metrics

Correctness
4.87
Faithfulness
4.90
Grounding
4.90
Relevance
4.97
Completeness
4.60
Overall
4.85

Latency Distribution

Mean
36774ms
Min
9584ms
Max
104257ms

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked LLMs and smart retrieval built in. Upload your data, call the API, and get grounded answers from day one.

import { Agentset } from "agentset";

const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");

const results = await ns.search(
  "What is multi-head attention?"
);

for (const result of results) {
  console.log(result.text);
}

Compare Models

See how it stacks up

Compare GLM 4.6 with other top llms to understand the differences in performance, accuracy, and latency.