# Gemini 4 Neon - BenchAudit True Index Profile

**Integrity Profile: Balanced Signal**

> The Verdict: Consistent Frontier Performance Across Public and Private Evals. Gemini 4 Neon (evaluated at xhigh effort) delivers closely aligned results across private Top-Tier tests (93.1p) and legacy public benchmarks (91.5p), with a minimal +0.2p matched gap across 3 domains (8 matched evaluations).

- **Canonical URL:** https://benchaudit.org/models/gemini-4-neon__xhigh/
- **True Index Rank:** #3 of 44
- **Creator:** Google
- **Weights:** Closed / API
- **Clean Evals Avg (Tiers S & A):** 93.1p (7 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 91.5p (3 evals)
- **Low-Tier Boost (Matched Delta):** +0.2p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #1 | 97.3p | 3 |
| Coding & SWE | #3 | 95.5p | 1 |
| Math & Scientific Reasoning | #10 | 79.8p | 1 |

## 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 | 3 (97.3p) | 1 (81.6p) | -15.7p |
| Coding & SWE | 1 (95.5p) | 1 (92.9p) | -2.6p |
| Math & Scientific Reasoning | 1 (79.8p) | 1 (100.0p) | +20.2p |

## Audited Benchmark Performance of Gemini 4 Neon

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #1/50 | 100.0p |
| [LiveBench](https://benchaudit.org/benchmarks/livebench/) | Private / Fresh | General Knowledge & QA | #1/28 | 100.0p |
| [MKA (Multimodal Knowledge Agent)](https://benchaudit.org/benchmarks/mka/) | Private / Fresh | Agentic & Enterprise | #2/23 | 100.0p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #3/41 | 100.0p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #2/47 | 99.4p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #3/49 | 95.8p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #4/46 | 95.5p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #4/50 | 92.9p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #5/50 | 91.8p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #10/50 | 81.6p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #11/46 | 79.8p |
