---
title: "John Dave Manuel (@johneai)"
description: "Rank #488 of 1944 on the Superset leaderboard, tier 1."
canonical: https://superset.sh/johneai
last-updated: 2026-09-30
---

# John Dave Manuel (@johneai)

Rank #488 of 1944 on the Superset leaderboard, tier 1.

URL: https://superset.sh/johneai

## Standing

- Rank: #488 of 1944
- Tier: Button pusher
- Tokens: 17.42B all time
- Cost: $12003.31 API-equivalent
- Sessions: 3518
- Tracking: 2026-07-29 to 2026-09-29

## How this tier was reached

Tier is a weighted score across the axes measured for you, so a strong axis offsets a weak one. Operator needs a higher combined score, and cost also caps the tier on its own.
Scored on 4 axes, measured over the trailing 30 days.

| Axis | Current | Needed | Met | Measures |
| --- | --- | --- | --- | --- |
| width | 3.5 | 3.1 | yes | agents running at once |
| depth | 4.0M | 10.4M | no | tokens per session |
| sustain | 28 | 17 | yes | active days in the last 30 |
| cost | $6892.10 | <= $315.60 | no | USD per merged PR, lower is better |

## Achievements

- **plant-floor** (level 2 of 3) at 30, earned 2026-09-29
- **ship-it** (level 1 of 4) at 1, earned 2026-09-29
- **thirty** (level 1 of 3) at 30, earned 2026-09-29
- **two-hands** (level 2 of 3) at 30, earned 2026-09-29
- **whole-task** (level 1 of 3) at 2.5M, earned 2026-09-29

## Milestones

- sessions: 1.0K
- spend: 10.0K
- tokens: 10.00B

## Contributions

- Active days in the last year: 61
- Busiest day: 2026-09-01 at 1.30B tokens

## Models

| Provider | Model | Tokens | Cost |
| --- | --- | --- | --- |
| codex | gpt-5.6-sol | 12.53B | $7069.17 |
| codex | gpt-6-astra | 2.60B | $3515.14 |
| claude | claude-fable-5 | 775.1M | $1099.45 |
| codex | gpt-5.4 | 446.5M | $101.86 |
| codex | codex-auto-review | 358.6M | $11.51 |
| codex | unknown | 340.2M | $5.23 |
| claude | claude-opus-5 | 163.8M | $124.93 |
| codex | gpt-5.3-codex-spark | 76.2M | $26.36 |

## Token breakdown

- Uncached input: 578.8M
- Cached input: 16.77B
- Cache write 5m: 10.5M
- Cache write 1h: 10.7M
- Output: 49.2M
- Reasoning output: 18.2M

Published voluntarily by the account holder. Source: https://superset.sh/johneai