Skip to main content

Model profile

GLM-4.7

Z.AIEstablishedReleased Oct 1, 2025
Data verified
Overall Score
61.16Public #42 of 200Verified #32 of 99
Arena Elo
1442
Eligible category ranks
2of 8
Price (1M tokens)
$0 in / $0 out
API pricing
Speed
82tok/s
Context
200K

Evidence coverage

30 of 321 tracked benchmarks are published. 10 are verified and 20 provisional. 7 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
30 / 321
Verified
10
Provisional
20
Categories with evidence
7 / 8

Evidence by category

  • Agentic8 benchmarks
    Mixed evidence
  • Coding6 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge9 benchmarks
    Mixed evidence
  • Math3 benchmarks
    Mixed evidence
  • Multilingual0 benchmarks
    Not measured
  • Multimodal1 benchmark
    Reported
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostReasoning
Confidence:
Medium
base

GLM-4.7 ranks #42 out of 200 models on the public leaderboard with an overall score of 61.16/100. It also ranks #32 out of 99 on the 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 30 of 321 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 Agentic (#40), while its weakest is Coding (#44). This performance profile makes it particularly useful for coding agents, browser research, and computer-use workflows.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 60.5661.31

  1. Gemini 3 Pro Deep Think
    Google
    #4161.31
    Gemini 3 Pro Deep Think is #41 with a score of 61.31.
    Compare
  2. GLM-4.7Current model
    Z.AI
    #4261.16
    GLM-4.7 is #42 with a score of 61.16.
  3. Gemma 4 31B
    Google
    #4361.08
    Gemma 4 31B is #43 with a score of 61.08.
    Compare
  4. GPT-5.4 Pro
    OpenAI
    #4460.89
    GPT-5.4 Pro is #44 with a score of 60.89.
    Compare
  5. Qwen3.5-27B
    Alibaba
    #4560.7
    Qwen3.5-27B is #45 with a score of 60.7.
    Compare
  6. DeepSeek V4 Pro
    DeepSeek
    #4660.66
    DeepSeek V4 Pro is #46 with a score of 60.66.
    Compare
  7. Qwen3.5-122B-A10B
    Alibaba
    #4760.56
    Qwen3.5-122B-A10B is #47 with a score of 60.56.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Agentic67%
    Eligible cohort rank #40 of 119Category score 51.7
  2. Coding64%
    Eligible cohort rank #44 of 122Category score 53.1

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #40 of 119Percentile 67thWeight 22%8 benchmarksMixed sources51.7
CodingRank #44 of 122Percentile 64thWeight 20%6 benchmarksMixed sources53.1
ReasoningRank Not rankedWeight 17%2 benchmarksReported78.6
KnowledgeRank Not rankedWeight 12%9 benchmarksMixed sources34.3
MathRank Not rankedWeight 5%3 benchmarksMixed sources26.1
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%1 benchmarkReported70.0
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported88.0

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1442±6.112,098
Coding1485±12.12,410
Math1428±21.0703
Instruction Following1428±10.43,209
Creative Writing1405±13.41,916
Multi-turn1459±13.61,919
Hard Prompts1463±7.86,598
Hard Prompts (English)1473±10.73,092
Longer Query1452±10.63,088

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic8 benchmarks
Terminal-Bench 2.0Provider exact
41%Weighted 38%
Source: Z.AI: GLM-4.7Provenance: Provider exact
BrowseCompProvider exact
52%Weighted 28%
Source: Z.AI: GLM-4.7Provenance: Provider exact
VITA-BenchBenchmark exact
15.5%Display only
Source: VitaBench leaderboardProvenance: Benchmark exact
AA Agentic IndexReported

Artificial Analysis Agentic Index

25.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

95.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

39.95%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
GDPval-AAReported

GDPval-AA normalized

33.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported
1165Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding6 benchmarks
LiveCodeBenchProvider exact

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

84.9%Weighted 38%
Source: Z.AI: GLM-4.7Provenance: Provider exact
SWE-RebenchBenchmark exact
58.7%Weighted 20%
Source: SWE-Rebench leaderboardProvenance: Live default SWE-Rebench leaderboard lists GLM-4.7 at 58.7% resolved rate.
SWE-bench VerifiedProvider exact

Software Engineering Benchmark Verified

73.8%Weighted 16%
Source: Z.AI: GLM-4.7Provenance: Provider exact
AA Coding IndexReported

Artificial Analysis Coding Index

45.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

45.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA LiveCodeBenchReported

Artificial Analysis LiveCodeBench

89.4%Display only
Source: Artificial Analysis: livecodebench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

64.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

1.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge9 benchmarks
HLEProvider exact

Humanity's Last Exam

24.8%Weighted 45%
Source: Z.AI: GLM-4.7Provenance: Provider exact
MMLU-ProReported

Massive Multitask Language Understanding Professional

84.3%Weighted 30%
Source: Reported upstream sourceProvenance: Reported row carried from an upstream public source. Displayable on BenchLM, but not treated as verified unless explicitly marked otherwise.
GPQAReported

Graduate-Level Google-Proof Q&A

85.7%Weighted 7%
Source: Reported upstream sourceProvenance: Reported row carried from an upstream public source. Displayable on BenchLM, but not treated as verified unless explicitly marked otherwise.
Artificial Analysis Intelligence IndexReported
33.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

85.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

25.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-34.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

29.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

90.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math3 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

2.439%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 2.439% for zai-org/GLM-4.7. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

0.000%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 0% for zai-org/GLM-4.7. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
AIME 2025Reported

American Invitational Mathematics Examination 2025

95.7%Display only
Source: Reported upstream sourceProvenance: Reported row carried from an upstream public source. Displayable on BenchLM, but not treated as verified unless explicitly marked otherwise.
Multimodal1 benchmark
Design Arena WebsiteReported

Design Arena Website Elo

1258Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

67.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does GLM-4.7 perform overall in AI benchmarks?

GLM-4.7 currently ranks #42 out of 200 models on BenchLM's provisional leaderboard with an overall score of 61.16. It also ranks #32 out of 99 on the verified leaderboard. It is created by Z.AI. Its published context window is 200K.

Is GLM-4.7 good for knowledge and understanding?

GLM-4.7 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is GLM-4.7 good for coding and programming?

GLM-4.7 ranks #44 out of 122 models in coding and programming benchmarks with an average score of 53.1. There are stronger options in this category.

Is GLM-4.7 good for mathematics?

GLM-4.7 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is GLM-4.7 good for reasoning and logic?

GLM-4.7 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

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 51.7. There are stronger options in this category.

Is GLM-4.7 good for multimodal and grounded tasks?

GLM-4.7 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is GLM-4.7 good for instruction following?

GLM-4.7 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

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 30 published benchmark scores out of the 321 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 published context window of 200K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.