# Gemini 3.8 Flash - BenchAudit True Index Profile

**Integrity Profile: High Contamination Vulnerability**

> The Verdict: Strong on Public Leaderboards, Vulnerable to Fresh Evals. Gemini 3.8 Flash (evaluated at high effort) shows a wide divergence between public benchmark claims (42.2p) and private evaluation performance (32.6p), with a +14.9p Low-Tier Boost across 4 matched domains, especially in General Knowledge & QA (+25.1p boost) and Math & Scientific Reasoning (+9.5p boost). Treat legacy leaderboard scores cautiously and anchor decisions on its Top-Tier S & A results.

- **Canonical URL:** https://benchaudit.org/models/gemini-3-8-flash__high/
- **True Index Rank:** #35 of 44
- **Creator:** Google
- **Weights:** Closed / API
- **Clean Evals Avg (Tiers S & A):** 32.6p (16 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 42.2p (7 evals)
- **Low-Tier Boost (Matched Delta):** +14.9p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #36 | 31.9p | 5 |
| Coding & SWE | #36 | 25.6p | 5 |
| Math & Scientific Reasoning | #38 | 23.9p | 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 | 5 (31.9p) | 2 (32.6p) | +0.7p |
| Coding & SWE | 5 (25.6p) | 1 (28.6p) | +3.0p |
| General Knowledge & QA | 3 (49.1p) | 1 (74.2p) | +25.1p |
| Math & Scientific Reasoning | 3 (23.9p) | 3 (33.4p) | +9.5p |

## Audited Benchmark Performance of Gemini 3.8 Flash

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [MMMU-Pro](https://benchaudit.org/benchmarks/mmmu-pro/) | Public / Aging | General Knowledge & QA | #5/22 | 74.2p |
| [ARC-AGI-2](https://benchaudit.org/benchmarks/arc-agi-2/) | Private / Fresh | General Knowledge & QA | #11/22 | 62.1p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #20/49 | 60.4p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #21/47 | 57.9p |
| [AA-AnalystAgent](https://benchaudit.org/benchmarks/aa-analystagent/) | Private / Fresh | Agentic & Enterprise | #13/24 | 51.1p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #26/50 | 49.0p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #26/41 | 42.2p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #30/50 | 40.8p |
| [AA-3D](https://benchaudit.org/benchmarks/aa-3d/) | Private / Fresh | Coding & SWE | #18/22 | 36.9p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #24/40 | 36.6p |
| [HealthBench](https://benchaudit.org/benchmarks/healthbench/) | Public / Aging | Math & Scientific Reasoning | #16/16 | 33.1p |
| [VIALS-AA](https://benchaudit.org/benchmarks/vials-aa/) | Semi-Exposed | Math & Scientific Reasoning | #16/23 | 31.8p |
| [MKA (Multimodal Knowledge Agent)](https://benchaudit.org/benchmarks/mka/) | Private / Fresh | Agentic & Enterprise | #20/23 | 30.0p |
| [Harvey LAB-AA v1.1](https://benchaudit.org/benchmarks/harvey-lab-aa-v1-1/) | Private / Fresh | Agentic & Enterprise | #21/21 | 29.6p |
| [CyberBench v1.1](https://benchaudit.org/benchmarks/cyberbench/) | Private / Fresh | Coding & SWE | #21/25 | 28.6p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #36/50 | 28.6p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #34/46 | 27.8p |
| [LiveBench](https://benchaudit.org/benchmarks/livebench/) | Private / Fresh | General Knowledge & QA | #25/28 | 27.3p |
| [FrontierMath](https://benchaudit.org/benchmarks/frontiermath/) | Private / Fresh | Math & Scientific Reasoning | #25/27 | 26.7p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #21/23 | 24.9p |
| [Code2Video-AA](https://benchaudit.org/benchmarks/code2video-aa/) | Private / Fresh | Coding & SWE | #20/23 | 18.9p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #35/43 | 16.2p |
| [Code Migration v1.1](https://benchaudit.org/benchmarks/code-migration-v1-1/) | Private / Fresh | Coding & SWE | #21/24 | 15.7p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #45/46 | 8.4p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #46/50 | 8.2p |
