---
title: "Score a set of resolved forecasts"
method: POST
path: "/benchmark/score"
tags: ["System"]
---

# Score a set of resolved forecasts

`POST /benchmark/score`

## Request

- Base URL: `https://foresea.ink` (the document declares no server; this is the origin it was published from)
- URL: `https://foresea.ink/benchmark/score`
- Auth: none declared

Grade any forecaster's resolved predictions: Brier score, accuracy, ECE
(calibration), and — when market prices are supplied — skill vs the market.
Lets you benchmark an LLM, a person, or another model against the same yardstick
Foresea grades itself on.

## Request body

- BenchmarkRequest: Score any forecaster's resolved calls — an AI-forecaster benchmark.
  - `forecasts` BenchmarkForecast[], required
    - `probability` number, required: Forecast probability of YES (0–1).
    - `outcome` integer, required: Realized outcome: 1 (YES) or 0 (NO).
    - `market_probability` number, nullable: Market price at forecast time, for skill-vs-market.
    - `question` string, nullable
  - `label` string, nullable: Optional name for this forecaster/run.

## Response `200`

Successful Response

- object

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/foresea/apis/foresea-intelligence-api.md) · [All operations](https://skmtc.dev/foresea/apis/foresea-intelligence-api/llms.txt) · [OpenAPI document](https://skmtc.dev/foresea/apis/foresea-intelligence-api/revisions/b03e49f4385d?raw)