# Claude Fable 5.2 - BenchAudit True Index Profile

**Integrity Profile: Clean Generalization**

> The Verdict: Holds Up Strongly on Private, Leak-Resistant Evals. Claude Fable 5.2 (evaluated at max effort) outperforms its legacy benchmark standing (88.5p) when moved to private, leak-resistant evaluations (95.3p), posting a -6.6p Low-Tier Boost across 3 matched domains, particularly in Agentic & Enterprise (-15.6p boost)—a strong indicator of genuine generalization.

- **Canonical URL:** https://benchaudit.org/models/claude-fable-5-2__max/
- **True Index Rank:** #2 of 44
- **Creator:** Anthropic
- **Weights:** Closed / API
- **Clean Evals Avg (Tiers S & A):** 95.3p (13 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 88.5p (8 evals)
- **Low-Tier Boost (Matched Delta):** -6.6p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #5 | 90.7p | 4 |
| Coding & SWE | #2 | 97.1p | 3 |
| Math & Scientific Reasoning | #2 | 96.9p | 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 (90.7p) | 2 (75.0p) | -15.6p |
| Coding & SWE | 3 (97.1p) | 2 (93.3p) | -3.8p |
| Math & Scientific Reasoning | 3 (96.9p) | 4 (97.1p) | +0.2p |

## Audited Benchmark Performance of Claude Fable 5.2

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #1/47 | 100.0p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #1/23 | 100.0p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #1/46 | 100.0p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #1/49 | 100.0p |
| [MKA (Multimodal Knowledge Agent)](https://benchaudit.org/benchmarks/mka/) | Private / Fresh | Agentic & Enterprise | #1/23 | 100.0p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #1/46 | 100.0p |
| [SWE Atlas - Codebase QnA](https://benchaudit.org/benchmarks/swe-atlas-qna/) | Public / Aging | Coding & SWE | #1/15 | 100.0p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #2/41 | 100.0p |
| [VIALS-AA](https://benchaudit.org/benchmarks/vials-aa/) | Semi-Exposed | Math & Scientific Reasoning | #1/23 | 100.0p |
| [FrontierMath](https://benchaudit.org/benchmarks/frontiermath/) | Private / Fresh | Math & Scientific Reasoning | #1/27 | 99.5p |
| [AA-3D](https://benchaudit.org/benchmarks/aa-3d/) | Private / Fresh | Coding & SWE | #2/22 | 98.8p |
| [LiveBench](https://benchaudit.org/benchmarks/livebench/) | Private / Fresh | General Knowledge & QA | #4/28 | 97.9p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #3/50 | 95.9p |
| [Autoform-Hard](https://benchaudit.org/benchmarks/autoform-hard/) | Public / Aging | Math & Scientific Reasoning | #2/8 | 94.9p |
| [HealthBench](https://benchaudit.org/benchmarks/healthbench/) | Public / Aging | Math & Scientific Reasoning | #3/16 | 93.5p |
| [Code Migration v1.1](https://benchaudit.org/benchmarks/code-migration-v1-1/) | Private / Fresh | Coding & SWE | #2/24 | 92.6p |
| [ARC-AGI-2](https://benchaudit.org/benchmarks/arc-agi-2/) | Private / Fresh | General Knowledge & QA | #4/22 | 91.9p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #5/50 | 91.8p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #1/40 | 91.1p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #5/43 | 86.8p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #7/50 | 86.7p |
| [Harvey LAB-AA v1.1](https://benchaudit.org/benchmarks/harvey-lab-aa-v1-1/) | Private / Fresh | Agentic & Enterprise | #9/21 | 75.0p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #19/50 | 63.3p |
