# GLM-4.7 Benchmark Scores & Performance

> GLM-4.7 by Z.AI scores 48.85/100 overall, ranking #103 out of 954 AI models.

Canonical page: https://benchlm.ai/models/glm-4-7

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Z.AI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 200K |
| Overall Score | 48.85/100 |
| Overall Rank | #103 of 954 |

## Family & Coverage

- Family: GLM-4.7
- Variant: base
- Benchmarks covered: 32 of 639
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 41% | [Z.AI: GLM-4.7](https://docs.z.ai/guides/llm/glm-4.7) |
| [BrowseComp](/benchmarks/browsecomp) | 52% | [Z.AI: GLM-4.7](https://docs.z.ai/guides/llm/glm-4.7) |
| [VITA-Bench](/benchmarks/vitabench) | 15.5% | [VitaBench leaderboard](https://vitabench.github.io/) |
| [τ²-bench results](/benchmarks/tau2-bench) | 95.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [Gert Labs](/benchmarks/gertlabs) | 39.95% | [Gert Labs rankings](https://gertlabs.com/rankings) |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 25.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1096 | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 73.8% | [Z.AI: GLM-4.7](https://docs.z.ai/guides/llm/glm-4.7) |
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 84.9% | [GLM-4.7 model card](https://huggingface.co/zai-org/GLM-4.7) |
| [SWE-Rebench](/benchmarks/swe-rebench) | 58.7% | [SWE-Rebench leaderboard](https://swe-rebench.com/) |
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 41.0% | [Z.AI: GLM-4.7](https://docs.z.ai/guides/llm/glm-4.7) |
| [AA LiveCodeBench](/benchmarks/aalivecodebench) | 89.4% | [Artificial Analysis: livecodebench leaderboard](https://artificialanalysis.ai/evaluations/livecodebench) |
| [AA Coding Index](/benchmarks/aacodingindex) | 45.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [LiveCodeBench (Vals)](/benchmarks/valslivecodebench) | 82.2% | [Vals AI: LiveCodeBench leaderboard](https://www.vals.ai/models/zai_glm-4.7) |
| [SWE-bench (Vals)](/benchmarks/valsswebench) | 69.4% | [Vals AI: SWE-bench leaderboard](https://www.vals.ai/models/zai_glm-4.7) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Design Arena Website](/benchmarks/designarenawebsite) | 1227 | [OpenRouter model benchmarks](https://openrouter.ai/z-ai/glm-4.7/benchmarks) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 71.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [CritPt](/benchmarks/critpt) | 1.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 85.7% | [Reported upstream source](https://z.ai/blog/glm-4.7) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 84.3% | [Reported upstream source](https://z.ai/blog/glm-4.7) |
| [HLE](/benchmarks/hle) | 24.8% | [Z.AI: GLM-4.7](https://docs.z.ai/guides/llm/glm-4.7) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 22.2% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 85.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [AA-HLE](/benchmarks/aahle) | 27.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -36.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 29.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 93.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |
| [GPQA Diamond (Vals)](/benchmarks/gpqa-diamond) | 80.1% | [Vals AI: GPQA Diamond leaderboard](https://www.vals.ai/models/zai_glm-4.7) |
| [MMLU-Pro (Vals)](/benchmarks/mmlu-pro) | 82.7% | [Vals AI: MMLU Pro leaderboard](https://www.vals.ai/models/zai_glm-4.7) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-IFBench](/benchmarks/ifbench) | 67.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/glm-4-7) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME 2025](/benchmarks/aime2025) | 95.7% | [Reported upstream source](https://z.ai/blog/glm-4.7) |
| [HMMT Feb 2025](/benchmarks/hmmtfeb2025) | 97.1% | [GLM-4.7 model card](https://huggingface.co/zai-org/GLM-4.7) |

## Other Z.AI Models

- [GLM-5.3](/models/glm-5-3) - Score: 67.88
- [GLM-5.2](/models/glm-5-2) - Score: 60.5
- [GLM-5.3-Flash](/models/glm-5-3-flash) - Score: 58.52
- [GLM-5.1](/models/glm-5-1) - Score: 56.31
- [GLM-5](/models/glm-5) - Score: 54.84
- [GLM-5-Turbo](/models/glm-5-turbo) - Score: 53.19
- [GLM-5V-Turbo](/models/glm-5v-turbo) - Score: 49.6
- [GLM-4.6](/models/glm-4-6) - Score: 40.02
- [GLM-4.7-Flash](/models/glm-4-7-flash) - Score: 39.13
- [GLM-4.5-Air](/models/glm-4-5-air) - Score: 34.93
- [GLM-4.5](/models/glm-4-5) - Score: not computed
- [GLM-5 (Reasoning)](/models/glm-5-reasoning) - Score: not computed