# Gemini 4 Carbon - BenchAudit True Index Profile

**Integrity Profile: Moderate Public Lift**

> The Verdict: Modest Legacy Lift Over Private Evaluations. Gemini 4 Carbon (evaluated at high effort) scores slightly higher on older public tests (87.4p) than on private, fresh evaluations (84.6p), yielding a +3.9p Low-Tier Boost across 3 domains, led by Math & Scientific Reasoning (+16.2p boost) and Coding & SWE (+9.2p boost).

- **Canonical URL:** https://benchaudit.org/models/gemini-4-carbon__high/
- **True Index Rank:** #4 of 44
- **Creator:** Google
- **Weights:** Closed / API
- **Clean Evals Avg (Tiers S & A):** 84.6p (10 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 87.4p (5 evals)
- **Low-Tier Boost (Matched Delta):** +3.9p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #4 | 91.0p | 3 |
| Coding & SWE | #5 | 88.8p | 2 |
| Math & Scientific Reasoning | #14 | 68.6p | 2 |

## 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 (91.0p) | 2 (79.3p) | -11.7p |
| Coding & SWE | 2 (88.8p) | 1 (98.0p) | +9.2p |
| Math & Scientific Reasoning | 2 (68.6p) | 2 (84.8p) | +16.2p |

## Audited Benchmark Performance of Gemini 4 Carbon

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [MKA (Multimodal Knowledge Agent)](https://benchaudit.org/benchmarks/mka/) | Private / Fresh | Agentic & Enterprise | #3/23 | 99.6p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #2/50 | 98.0p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #2/50 | 98.0p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #3/47 | 97.3p |
| [Vibe Code Bench 1-100 v1.1](https://benchaudit.org/benchmarks/vcb-1-100-v1-1/) | Private / Fresh | Coding & SWE | #2/10 | 95.6p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #5/41 | 95.0p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #4/49 | 93.8p |
| [VIALS-AA](https://benchaudit.org/benchmarks/vials-aa/) | Semi-Exposed | Math & Scientific Reasoning | #3/23 | 90.9p |
| [FrontierMath](https://benchaudit.org/benchmarks/frontiermath/) | Private / Fresh | Math & Scientific Reasoning | #5/27 | 89.9p |
| [LiveBench](https://benchaudit.org/benchmarks/livebench/) | Private / Fresh | General Knowledge & QA | #7/28 | 87.8p |
| [ARC-AGI-2](https://benchaudit.org/benchmarks/arc-agi-2/) | Private / Fresh | General Knowledge & QA | #6/22 | 85.1p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #9/50 | 83.7p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #10/46 | 81.9p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #13/50 | 75.5p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #10/43 | 75.0p |
| [Autoform-Hard](https://benchaudit.org/benchmarks/autoform-hard/) | Public / Aging | Math & Scientific Reasoning | #4/8 | 74.5p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #26/46 | 47.2p |
