# GLM-5.3 - BenchAudit True Index Profile

**Contamination Sensitivity: Elevated**

> The Verdict: Strong on Public Leaderboards, Vulnerable to Fresh Evals. GLM-5.3 (evaluated at max effort) shows a noticeable divergence between public benchmark claims (51.8p) and private evaluation performance (40.8p), posting a +6.0p Low-Tier Boost across 3 matched domains, especially in Math & Scientific Reasoning (+20.0p boost) and Coding & SWE (+19.3p boost). Private tests reveal meaningful headroom beneath its legacy scores.

- **Canonical URL:** https://benchaudit.org/models/glm-5-3__max/
- **True Index Rank:** #29 of 44
- **Creator:** Z AI
- **Weights:** Open Weights
- **Clean Evals Avg (Tiers S & A):** 40.8p (14 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 51.8p (5 evals)
- **Low-Tier Boost (Matched Delta):** +6.0p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #32 | 41.6p | 4 |
| Coding & SWE | #29 | 47.1p | 6 |
| Math & Scientific Reasoning | #32 | 36.3p | 3 |

## Head-to-Head: Clean Evals vs. Legacy Benchmarks

| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | 4 (41.6p) | 2 (32.8p) | -8.8p |
| Coding & SWE | 6 (47.1p) | 2 (66.3p) | +19.3p |
| Math & Scientific Reasoning | 3 (36.3p) | 1 (56.3p) | +20.0p |

## Audited Benchmark Performance of GLM-5.3

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [SWE Atlas - Codebase QnA](https://benchaudit.org/benchmarks/swe-atlas-qna/) | Public / Aging | Coding & SWE | #7/15 | 69.4p |
| [Vibe Code Bench 1-100 v1.1](https://benchaudit.org/benchmarks/vcb-1-100-v1-1/) | Private / Fresh | Coding & SWE | #5/10 | 68.0p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #19/50 | 63.3p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #17/43 | 58.5p |
| [HealthBench](https://benchaudit.org/benchmarks/healthbench/) | Public / Aging | Math & Scientific Reasoning | #11/16 | 56.3p |
| [Code Migration v1.1](https://benchaudit.org/benchmarks/code-migration-v1-1/) | Private / Fresh | Coding & SWE | #11/24 | 56.2p |
| [CyberBench v1.1](https://benchaudit.org/benchmarks/cyberbench/) | Private / Fresh | Coding & SWE | #13/25 | 53.9p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #25/50 | 51.0p |
| [Code2Video-AA](https://benchaudit.org/benchmarks/code2video-aa/) | Private / Fresh | Coding & SWE | #12/23 | 48.2p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #27/50 | 46.9p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #22/40 | 41.4p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #30/47 | 38.2p |
| [AA-AnalystAgent](https://benchaudit.org/benchmarks/aa-analystagent/) | Private / Fresh | Agentic & Enterprise | #18/24 | 35.1p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #32/46 | 34.6p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #31/46 | 34.5p |
| [Harvey LAB-AA v1.1](https://benchaudit.org/benchmarks/harvey-lab-aa-v1-1/) | Private / Fresh | Agentic & Enterprise | #20/21 | 33.4p |
| [FrontierMath](https://benchaudit.org/benchmarks/frontiermath/) | Private / Fresh | Math & Scientific Reasoning | #23/27 | 33.0p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #38/49 | 22.9p |
| [AA-3D](https://benchaudit.org/benchmarks/aa-3d/) | Private / Fresh | Coding & SWE | #22/22 | 21.5p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #46/50 | 7.1p |
