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

# kong eval

> Score analysis output against ground-truth source code

## Synopsis

```bash theme={null}
kong eval ANALYSIS_JSON SOURCE_FILE
```

## Description

Compare Kong's analysis output against ground-truth source code. Computes symbol accuracy (name matching) and type accuracy (signature matching) for each function, then reports aggregate scores.

## Arguments

| Argument        | Type | Required | Description                                 |
| --------------- | ---- | -------- | ------------------------------------------- |
| `ANALYSIS_JSON` | Path | Yes      | Path to Kong's `analysis.json` output file. |
| `SOURCE_FILE`   | Path | Yes      | Path to the ground-truth C source file.     |

## Example

```bash theme={null}
kong eval ./kong_output/analysis.json ./original_source.c
```

Output:

```
Binary: binary
Functions: 156 analyzed / 200 in source
Symbol Accuracy: 87.3%
Type Accuracy: 72.1%

Per-Function Scores:
  OK parse_http_header             -> parse_http_header  sym=1.00  type=0.95
  ~~ process_data                  -> process_request    sym=0.60  type=0.45
  NO FUN_00401000                  -> (no match)         sym=0.00  type=0.00
```

## Further reading

* [Evaluating Results](/usage/evaluating-results) — detailed scoring methodology
* [Interpreting Kong Output](/case-studies/interpreting-output) — understanding output fields