# Muse Spark 1.3 - BenchAudit True Index Profile

**Integrity Profile: High Contamination Vulnerability**

> The Verdict: Strong on Public Leaderboards, Vulnerable to Fresh Evals. Muse Spark 1.3 (evaluated at max effort) shows a wide divergence between public benchmark claims (55.8p) and private evaluation performance (49.6p), with a +16.2p Low-Tier Boost across 3 matched domains, especially in Agentic & Enterprise (+18.6p boost). Treat legacy leaderboard scores cautiously and anchor decisions on its Top-Tier S & A results.

- **Canonical URL:** https://benchaudit.org/models/muse-spark-1-3__max/
- **True Index Rank:** #25 of 44
- **Creator:** Meta
- **Weights:** Closed / API
- **Clean Evals Avg (Tiers S & A):** 49.6p (13 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 55.8p (4 evals)
- **Low-Tier Boost (Matched Delta):** +16.2p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #21 | 54.2p | 4 |
| Coding & SWE | #28 | 47.8p | 4 |
| Math & Scientific Reasoning | #25 | 45.0p | 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 (54.2p) | 2 (72.8p) | +18.6p |
| Coding & SWE | 4 (47.8p) | 1 (50.0p) | +2.2p |
| Math & Scientific Reasoning | 3 (45.0p) | 1 (44.7p) | -0.3p |

## Audited Benchmark Performance of Muse Spark 1.3

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [Harvey LAB-AA v1.1](https://benchaudit.org/benchmarks/harvey-lab-aa-v1-1/) | Private / Fresh | Agentic & Enterprise | #7/21 | 82.6p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #12/50 | 77.6p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #15/50 | 71.4p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #13/43 | 67.9p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #19/49 | 62.5p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #14/40 | 60.3p |
| [AA-3D](https://benchaudit.org/benchmarks/aa-3d/) | Private / Fresh | Coding & SWE | #12/22 | 60.1p |
| [CyberBench v1.1](https://benchaudit.org/benchmarks/cyberbench/) | Private / Fresh | Coding & SWE | #11/25 | 58.3p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #22/47 | 55.7p |
| [FrontierMath](https://benchaudit.org/benchmarks/frontiermath/) | Private / Fresh | Math & Scientific Reasoning | #16/27 | 50.4p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #25/50 | 50.0p |
| [LiveBench](https://benchaudit.org/benchmarks/livebench/) | Private / Fresh | General Knowledge & QA | #19/28 | 47.5p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #25/41 | 44.7p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #29/46 | 39.1p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #33/50 | 34.7p |
| [Code2Video-AA](https://benchaudit.org/benchmarks/code2video-aa/) | Private / Fresh | Coding & SWE | #16/23 | 33.6p |
| [AA-AnalystAgent](https://benchaudit.org/benchmarks/aa-analystagent/) | Private / Fresh | Agentic & Enterprise | #20/24 | 28.0p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #37/46 | 24.2p |
