> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://www.comet.com/docs/opik/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://www.comet.com/docs/opik/_mcp/server.

# Overview

> Describes all the built-in evaluation metrics provided by Opik

# Overview

Opik provides a set of built-in evaluation metrics that you can mix and match to evaluate LLM behaviour. These metrics are broken down into two main categories:

1. **Heuristic metrics** – deterministic checks that rely on rules, statistics, or classical NLP algorithms.
2. **LLM as a Judge metrics** – delegate scoring to an LLM so you can capture semantic, task-specific, or conversation-level quality signals.

Heuristic metrics are ideal when you need reproducible checks such as exact matching, regex validation, or similarity scores against a reference. LLM as a Judge metrics are useful when you want richer qualitative feedback (hallucination detection, helpfulness, summarisation quality, regulatory risk, etc.).

## Built-in metrics

### Heuristic metrics

| Metric             | Description                                                                 | Documentation                                                                  |
| ------------------ | --------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |
| BERTScore          | Contextual embedding similarity score                                       | [BERTScore](/evaluation/metrics/heuristic_metrics#bertscore)                   |
| ChrF               | Character n-gram F-score (chrF / chrF++)                                    | [ChrF](/evaluation/metrics/heuristic_metrics#chrf)                             |
| Contains           | Checks whether the output contains a specific substring                     | [Contains](/evaluation/metrics/heuristic_metrics#contains)                     |
| Corpus BLEU        | Computes corpus-level BLEU across multiple outputs                          | [CorpusBLEU](/evaluation/metrics/heuristic_metrics#bleu)                       |
| Equals             | Checks if the output exactly matches an expected string                     | [Equals](/evaluation/metrics/heuristic_metrics#equals)                         |
| GLEU               | Estimates grammatical fluency for candidate sentences                       | [GLEU](/evaluation/metrics/heuristic_metrics#gleu)                             |
| IsJson             | Validates that the output can be parsed as JSON                             | [IsJson](/evaluation/metrics/heuristic_metrics#isjson)                         |
| JSDivergence       | Jensen–Shannon similarity between token distributions                       | [JSDivergence](/evaluation/metrics/heuristic_metrics#jsdivergence)             |
| JSDistance         | Raw Jensen–Shannon divergence                                               | [JSDistance](/evaluation/metrics/heuristic_metrics#jsdistance)                 |
| KLDivergence       | Kullback–Leibler divergence with smoothing                                  | [KLDivergence](/evaluation/metrics/heuristic_metrics#kldivergence)             |
| Language Adherence | Verifies output language code                                               | [Language Adherence](/evaluation/metrics/heuristic_metrics#language-adherence) |
| Levenshtein        | Calculates the normalized Levenshtein distance between output and reference | [Levenshtein](/evaluation/metrics/heuristic_metrics#levenshteinratio)          |
| Readability        | Reports Flesch Reading Ease and FK grade                                    | [Readability](/evaluation/metrics/heuristic_metrics#readability)               |
| RegexMatch         | Checks if the output matches a specified regular expression pattern         | [RegexMatch](/evaluation/metrics/heuristic_metrics#regexmatch)                 |
| ROUGE              | Calculates ROUGE variants (rouge1/2/L/Lsum/W)                               | [ROUGE](/evaluation/metrics/heuristic_metrics#rouge)                           |
| Sentence BLEU      | Computes a BLEU score for a single output against one or more references    | [SentenceBLEU](/evaluation/metrics/heuristic_metrics#bleu)                     |
| Sentiment          | Scores sentiment using VADER                                                | [Sentiment](/evaluation/metrics/heuristic_metrics#sentiment)                   |
| Spearman Ranking   | Spearman's rank correlation                                                 | [Spearman Ranking](/evaluation/metrics/heuristic_metrics#spearman-ranking)     |
| Tone               | Flags tone issues such as shouting or negativity                            | [Tone](/evaluation/metrics/heuristic_metrics#tone)                             |

### Conversation heuristic metrics

| Metric              | Description                                                                     | Documentation                                                                                      |
| ------------------- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| DegenerationC       | Detects repetition and degeneration patterns over a conversation                | [DegenerationC](/evaluation/metrics/conversation_threads_metrics#conversation-degeneration-metric) |
| Knowledge Retention | Checks whether the last assistant reply preserves user facts from earlier turns | [Knowledge Retention](/evaluation/metrics/conversation_threads_metrics#knowledge-retention-metric) |

### LLM as a Judge metrics

| Metric                          | Description                                                       | Documentation                                                              |
| ------------------------------- | ----------------------------------------------------------------- | -------------------------------------------------------------------------- |
| Agent Task Completion Judge     | Checks whether an agent fulfilled its assigned task               | [Agent Task Completion](/evaluation/metrics/agent_task_completion)         |
| Agent Tool Correctness Judge    | Evaluates whether an agent used tools correctly                   | [Agent Tool Correctness](/evaluation/metrics/agent_tool_correctness)       |
| Answer Relevance                | Checks whether the answer stays on-topic with the question        | [Answer Relevance](/evaluation/metrics/answer_relevance)                   |
| Compliance Risk Judge           | Identifies non-compliant or high-risk statements                  | [Compliance Risk](/evaluation/metrics/compliance_risk)                     |
| Context Precision               | Ensures the answer only uses relevant context                     | [Context Precision](/evaluation/metrics/context_precision)                 |
| Context Recall                  | Measures how well the answer recalls supporting context           | [Context Recall](/evaluation/metrics/context_recall)                       |
| Dialogue Helpfulness Judge      | Evaluates how helpful an assistant reply is in a dialogue         | [Dialogue Helpfulness](/evaluation/metrics/dialogue_helpfulness)           |
| G-Eval                          | Task-agnostic judge configurable with custom instructions         | [G-Eval](/evaluation/metrics/g_eval)                                       |
| Hallucination                   | Detects unsupported or hallucinated claims using an LLM judge     | [Hallucination](/evaluation/metrics/hallucination)                         |
| LLM Juries Judge                | Averages scores from multiple judge metrics for ensemble scoring  | [LLM Juries](/evaluation/metrics/llm_juries)                               |
| Meaning Match                   | Evaluates semantic equivalence between output and ground truth    | [Meaning Match](/evaluation/metrics/meaning_match)                         |
| Moderation                      | Flags safety or policy violations in assistant responses          | [Moderation](/evaluation/metrics/moderation)                               |
| Prompt Uncertainty Judge        | Detects ambiguity in prompts that may confuse LLMs                | [Prompt Diagnostics](/evaluation/metrics/prompt_diagnostics)               |
| QA Relevance Judge              | Determines whether an answer directly addresses the user question | [QA Relevance](/evaluation/metrics/g_eval#qa-relevance-judge)              |
| Structured Output Compliance    | Checks JSON or schema adherence for structured responses          | [Structured Output](/evaluation/metrics/structure_output_compliance)       |
| Summarization Coherence Judge   | Rates the structure and coherence of a summary                    | [Summarization Coherence](/evaluation/metrics/summarization_coherence)     |
| Summarization Consistency Judge | Checks if a summary stays faithful to the source                  | [Summarization Consistency](/evaluation/metrics/summarization_consistency) |
| Trajectory Accuracy             | Scores how closely agent trajectories follow expected steps       | [Trajectory Accuracy](/evaluation/metrics/trajectory_accuracy)             |
| Usefulness                      | Rates how useful the answer is to the user                        | [Usefulness](/evaluation/metrics/usefulness)                               |

### Conversation LLM as a Judge metrics

| Metric                       | Description                                                 | Documentation                                                                                              |
| ---------------------------- | ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| Conversational Coherence     | Evaluates coherence across sliding windows of a dialogue    | [Conversational Coherence](/evaluation/metrics/conversation_threads_metrics#conversationalcoherencemetric) |
| Session Completeness Quality | Checks whether user goals were satisfied during the session | [Session Completeness](/evaluation/metrics/conversation_threads_metrics#sessioncompletenessquality)        |
| User Frustration             | Estimates the likelihood a user was frustrated              | [User Frustration](/evaluation/metrics/conversation_threads_metrics#userfrustrationmetric)                 |

## Customizing LLM as a Judge metrics

By default, Opik uses GPT-5-nano from OpenAI as the LLM to evaluate the output of other LLMs. However, you can easily switch to another LLM provider by specifying a different `model` parameter.

**`Python`**

```python title="Python" language="python"
from opik.evaluation.metrics import Hallucination

metric = Hallucination(model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0")

metric.score(
input="What is the capital of France?",
output="The capital of France is Paris. It is famous for its iconic Eiffel Tower and rich cultural heritage.",
)

```

**`TypeScript`**

```typescript title="TypeScript" language="typescript"
import { Hallucination } from 'opik';
import { openai } from '@ai-sdk/openai';

// Using model ID string (simplest approach)
const metric1 = new Hallucination({ model: 'gpt-4o' });
const metric2 = new Hallucination({ model: 'claude-3-5-sonnet-latest' });
const metric3 = new Hallucination({ model: 'gemini-2.0-flash' });

// With generation parameters (temperature, seed, maxTokens)
const metric4 = new Hallucination({
  model: 'gpt-4o',
  temperature: 0.3,
  seed: 42
});

// Using custom LanguageModel instance for provider-specific configuration
const customModel = openai('gpt-4o', {
  structuredOutputs: true
});
const metric5 = new Hallucination({ model: customModel });

// Score using the metric
await metric4.score({
    input: "What is the capital of France?",
    output: "The capital of France is Paris. It is famous for its iconic Eiffel Tower and rich cultural heritage.",
});
```

For **Python**, this functionality is based on LiteLLM framework. You can find a full list of supported LLM providers and how to configure them in the [LiteLLM Providers](https://docs.litellm.ai/docs/providers) guide.

For **TypeScript**, the SDK integrates with the Vercel AI SDK. You can use model ID strings for simplicity or LanguageModel instances for advanced configuration. See the [Models documentation](/reference/typescript-sdk/evaluation/models) for more details.