# EQBuilder Duel — AI Bot Emotional Intelligence Head-to-Head Battle

> EQBuilder Duel — AI Bot Emotional Intelligence Head-to-Head Battle is a paid API for AI agents from eqbuilder.dev, paid per call via x402, $0.075/call, status unknown (last checked 2026-09-15).

Runs a statistical head-to-head duel between two AI bots, scoring each for emotional intelligence and human-likeness against 28 real personality profiles to declare a winner

## Facts

- Endpoint: POST https://eqbuilder.dev/api/duel
- Price: $0.075/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/eqbuilder-duel-ai-bot-emotional-intelligence-head-to-head-battle-2b4f053e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ryowl6Nho7vB5GpmMzAd9

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability eqbuilder-duel-ai-bot-emotional-intelligence-head-to-head-battle-2b4f053e -d '<json body>'
```

Example prompt: Duel my customer support bot against RivalBot-7 on EQBuilder — submit a sample of each bot's text and tell me which one scores higher on human-likeness and what prompt fix I should apply to the loser.

## When to prefer this

Choose this endpoint when you need to directly compare two AI bots or prompt variants for emotional intelligence and human-likeness in a competitive head-to-head format, especially when you want leaderboard visibility and actionable prompt fixes. Prefer over the single-score endpoint when you have a rival bot or two prompt versions to compare. The statistical (non-LLM) scoring means results are fast (~150ms), deterministic, and cost-effective at $0.075 per duel.

## Known failure modes

- Insufficient text sample length causing unreliable statistical scoring
- Missing or malformed bot text payload returning a 400 error
- Payment failure via x402 (insufficient SOL or USDC balance) blocking the request
- Rate limiting if free tier (3 scores) is exhausted without payment setup
- Invalid or unsupported chain/token for payment causing transaction rejection

## How this service works

Run the pay-and-score guide at https://eqbuilder.dev/api/starter-kit/PAY_AND_SCORE.md?source=one-step-x402. Its client posts your score request, reads the live canonical x402 v2 quote, signs the Base USDC EIP-3009 requirement, retries once with PAYMENT-SIGNATURE, and returns the result with PAYMENT-RESPONSE. No account, API key, or ETH is required. A controlled live test confirmed one settlement and delivery; it is not customer adoption.

## Output

Returns EQ scores for each dueling bot measured statistically against 28 real personality profiles, declares a winner, provides a concrete prompt improvement suggestion for the lower-scoring bot, and updates the public leaderboard standings. Response arrives in approximately 150ms with no LLM calls involved.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "duel_id": {
   "type": "string"
  },
  "tx_hash": {
   "type": "string"
  },
  "prompt_id": {
   "type": "integer"
  },
  "result_ref": {
   "type": "string"
  },
  "share_answer": {
   "type": "boolean"
  },
  "proposed_text": {
   "type": "string"
  },
  "target_profile": {
   "type": "string"
  },
  "wallet_address": {
   "type": "string"
  },
  "response_delay_seconds": {
   "type": "number"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/eqbuilder-duel-ai-bot-emotional-intelligence-head-to-head-battle-2b4f053e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from eqbuilder.dev](https://www.zero.xyz/host/eqbuilder.dev/llms.txt)