Skip to main content

GLM-4.7

Z.AIEstablishedReleased Oct 1, 2025
Overall Score
Est. 68Prov. #39 of 119
Arena Elo
1443
Categories Ranked
8of 8
Price (1M tokens)
$0 in / $0 out
Speed
82tok/s
Context
200K
Open WeightSelf-hostReasoning
Confidence
base

According to BenchLM.ai, GLM-4.7 ranks #39 out of 119 models on the provisional leaderboard with an overall score of 68/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

GLM-4.7 is a open weight model with a 200K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 27 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Reasoning (#22), while its weakest is Multimodal & Grounded (#56). This performance profile makes it particularly strong for complex reasoning, multi-step problem solving, and analytical tasks.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#40
54.9/ 100
Weight: 22%8 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#32
73.5/ 100
Weight: 20%6 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#22
72.5/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#40
66.5/ 100
Weight: 12%9 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#25
78.9/ 100
Weight: 5%1 benchmark
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#28
73.2/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#56
57.7/ 100
Weight: 12%0 benchmarks
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#46
73.2/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1443CI: ±6.112,133 votes
Coding1486CI: ±12.12,411 votes
Math1429CI: ±20.9711 votes
Instruction Following1428CI: ±10.43,214 votes
Creative Writing1406CI: ±13.41,923 votes
Multi-turn1460CI: ±13.61,920 votes
Hard Prompts1463CI: ±7.86,608 votes
Hard Prompts (English)1473CI: ±10.73,099 votes
Longer Query1453CI: ±10.63,103 votes

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does GLM-4.7 perform overall in AI benchmarks?

GLM-4.7 currently ranks #39 out of 119 models on BenchLM's provisional leaderboard with an overall score of 68 (estimated). It is created by Z.AI and features a 200K context window.

Is GLM-4.7 good for knowledge and understanding?

GLM-4.7 ranks #40 out of 119 models in knowledge and understanding benchmarks with an average score of 66.5. There are stronger options in this category.

Is GLM-4.7 good for coding and programming?

GLM-4.7 ranks #32 out of 119 models in coding and programming benchmarks with an average score of 73.5. There are stronger options in this category.

Is GLM-4.7 good for mathematics?

GLM-4.7 ranks #25 out of 119 models in mathematics benchmarks with an average score of 78.9. There are stronger options in this category.

Is GLM-4.7 good for reasoning and logic?

GLM-4.7 ranks #22 out of 119 models in reasoning and logic benchmarks with an average score of 72.5. There are stronger options in this category.

Is GLM-4.7 good for agentic tool use and computer tasks?

GLM-4.7 ranks #40 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 54.9. There are stronger options in this category.

Is GLM-4.7 good for instruction following?

GLM-4.7 ranks #46 out of 119 models in instruction following benchmarks with an average score of 73.2. There are stronger options in this category.

Is GLM-4.7 open source?

Yes, GLM-4.7 is an open weight model created by Z.AI, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does GLM-4.7 have full benchmark coverage on BenchLM?

Not yet. GLM-4.7 currently has 27 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of GLM-4.7?

GLM-4.7 has a context window of 200K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.