# GLM-4.6 Benchmark Scores & Performance

> GLM-4.6 by Z.AI scores 53.94/100 overall, ranking #107 out of 411 AI models.

Canonical page: https://benchlm.ai/models/glm-4-6

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Z.AI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 200K |
| Overall Score | 53.94/100 |
| Overall Rank | #107 of 411 |

## Family & Coverage

- Family: GLM-4.6
- Variant: base
- Benchmarks covered: 14 of 422
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 76.9% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Vibe Code Bench](/benchmarks/vibecodebench) | 3.09% |
| [AA-SciCode](/benchmarks/aascicode) | 33.1% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 28.3% |
| [CritPt](/benchmarks/critpt) | 0.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 23.4% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 63.2% |
| [AA-HLE](/benchmarks/aahle) | 5.5% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -31.7% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 21.4% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 67.6% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 36.7% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [FrontierMath v2 (Tiers 1-3)](/benchmarks/frontiermathv2tiers13) | 3.819% |
| [FrontierMath v2 (Tier 4)](/benchmarks/frontiermathv2tier4) | 2.128% |

## Other Z.AI Models

- [GLM-5.3](/models/glm-5-3) - Score: 68.46
- [GLM-5.2](/models/glm-5-2) - Score: 68.21
- [GLM-5.3-Flash](/models/glm-5-3-flash) - Score: 66.09
- [GLM-5.1](/models/glm-5-1) - Score: 64.41
- [GLM-5-Turbo](/models/glm-5-turbo) - Score: 64.14
- [GLM-5](/models/glm-5) - Score: 62.16
- [GLM-5V-Turbo](/models/glm-5v-turbo) - Score: 60.56
- [GLM-5 (Reasoning)](/models/glm-5-reasoning) - Score: 59.16
- [GLM-4.7](/models/glm-4-7) - Score: 58.99
- [GLM-4.5](/models/glm-4-5) - Score: 56.99
- [GLM-4.7-Flash](/models/glm-4-7-flash) - Score: 49.4
- [GLM-4.5-Air](/models/glm-4-5-air) - Score: 46.33