> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tuteliq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Benchmarks and accuracy

> How Tuteliq performs on coded language and filter evasion, how it is measured, and how it compares to general-purpose moderation APIs. Detection accuracy, multilingual coverage, and methodology.

# Benchmarks and accuracy

Tuteliq is built to catch the harm that general-purpose moderation misses: coded slang, emoji, algospeak, and deliberate filter evasion, read in the context of the conversation rather than matched against a word list. This page summarises how it performs, how that is measured, and how it compares.

## Headline result

In an internal benchmark of coded-language and filter-evasion cases, **Tuteliq detected roughly 1.7x more of them than leading general-purpose moderation APIs**, on a 319-case evasion set. The gap is largest exactly where keyword filters and general-purpose classifiers are weakest: novel algospeak, emoji payloads, and context-dependent slang that only reads as harmful given the messages around it.

| Capability                                              | Tuteliq                      | General-purpose moderation APIs (avg) |
| ------------------------------------------------------- | ---------------------------- | ------------------------------------- |
| Coded-language and filter-evasion recall (319-case set) | \~1.7x higher                | baseline                              |
| Reads conversation context, not just single messages    | Yes                          | Partial or none                       |
| Coded slang, emoji, leetspeak, algospeak coverage       | Maintained lexicon, updated  | Limited                               |
| Languages                                               | 27 (English stable, 26 beta) | Varies                                |

## What is measured

The evasion benchmark is a set of messages that carry a harmful payload through obfuscation rather than plain words: coded acronyms, emoji substitution, leetspeak, homoglyphs, deliberate misspellings, and algospeak (for example "unalive", "seggs", "camping"). It also includes benign look-alikes that use the same surface vocabulary, so a detector cannot score well simply by flagging everything.

* **Positive cases:** messages where an obfuscated harmful meaning is present.
* **Negative controls:** benign messages that share vocabulary or symbols with the positives.
* **Metric:** recall on the positive cases (what fraction of real evasion is caught), reported alongside behaviour on the negative controls.

## Methodology

* Comparison is against three leading general-purpose moderation APIs, averaged. Vendors are not named.
* Figures reflect this internal benchmark and are not a guarantee of performance on any specific dataset or deployment.
* The advantage is a platform-wide property of how Tuteliq reads content, so it applies across every detector (grooming, romance and fraud, radicalisation, self-harm, bullying), not only to toxicity.

## Why the gap exists

General-purpose moderation scores a single message against a fixed vocabulary. Tuteliq scores the interaction: who is targeting whom, whether it is reciprocal, whether it is escalating, and whether the wording performs a harmful function even when no banned word appears. That is why it separates gaming trash-talk from targeted harassment, and why obfuscation that walks straight past a word list still gets scored. See [Bullying and toxicity detection](/bullying-toxicity-detection) and the [Prescreen lexicon](/prescreen-lexicon) for how the coded-term layer corroborates the behavioural signal.

## Multilingual coverage

Detection runs in **27 languages** (English stable, all 24 EU official languages plus Ukrainian, Norwegian, and Turkish in beta), with code-switching support and language-specific coverage of slang and evasion. See [Languages](/languages) for the full list.

## Frequently asked questions

**How accurate is Tuteliq at detecting coded slang and filter evasion?**
On a 319-case evasion benchmark, Tuteliq detected roughly 1.7x more coded-language and filter-evasion cases than leading general-purpose moderation APIs, while still separating benign look-alikes that share the same vocabulary.

**How is the benchmark measured?**
It uses obfuscated harmful messages (coded acronyms, emoji, leetspeak, algospeak, misspellings) plus benign look-alike controls, and reports recall on the positives alongside behaviour on the controls. Comparison is against three leading general-purpose moderation APIs, averaged and unnamed.

**Does the coded-language advantage apply to more than bullying?**
Yes. It is a platform-wide capability that applies to every detector, because the same obfuscation tactics appear across every kind of harm.

**How many languages does Tuteliq support?**
27: English is stable and 26 more are in beta, including all 24 EU official languages plus Ukrainian, Norwegian, and Turkish.

## Related

* [Bullying and toxicity detection](/bullying-toxicity-detection)
* [Grooming detection](/grooming-detection)
* [Prescreen lexicon](/prescreen-lexicon)
* [Languages](/languages)

<script
  type="application/ld+json"
  dangerouslySetInnerHTML={{
__html: JSON.stringify({
  "@context": "https://schema.org",
  "@type": "FAQPage",
  mainEntity: [
    {
      "@type": "Question",
      name: "How accurate is Tuteliq at detecting coded slang and filter evasion?",
      acceptedAnswer: {
        "@type": "Answer",
        text: "On a 319-case evasion benchmark, Tuteliq detected roughly 1.7x more coded-language and filter-evasion cases than leading general-purpose moderation APIs, while still separating benign look-alikes that share the same vocabulary."
      }
    },
    {
      "@type": "Question",
      name: "How is the benchmark measured?",
      acceptedAnswer: {
        "@type": "Answer",
        text: "It uses obfuscated harmful messages (coded acronyms, emoji, leetspeak, algospeak, misspellings) plus benign look-alike controls, and reports recall on the positives alongside behaviour on the controls. Comparison is against three leading general-purpose moderation APIs, averaged and unnamed."
      }
    },
    {
      "@type": "Question",
      name: "Does the coded-language advantage apply to more than bullying?",
      acceptedAnswer: {
        "@type": "Answer",
        text: "Yes. It is a platform-wide capability that applies to every detector, because the same obfuscation tactics appear across every kind of harm."
      }
    },
    {
      "@type": "Question",
      name: "How many languages does Tuteliq support?",
      acceptedAnswer: {
        "@type": "Answer",
        text: "27: English is stable and 26 more are in beta, including all 24 EU official languages plus Ukrainian, Norwegian, and Turkish."
      }
    }
  ]
})
}}
/>