---
title: "Michael (@michael)"
description: "Rank #474 of 1205 on the Superset leaderboard, tier 2."
canonical: https://superset.sh/michael
last-updated: 2026-09-08
---

# Michael (@michael)

Rank #474 of 1205 on the Superset leaderboard, tier 2.

URL: https://superset.sh/michael

## Standing

- Rank: #474 of 1205
- Tier: Operator
- Tokens: 7.58B all time
- Cost: $5420.66 API-equivalent
- Sessions: 1887
- Tracking: 2026-08-01 to 2026-09-07

## How this tier was reached

Tier is a weighted score across the axes measured for you, so a strong axis offsets a weak one. Plant Manager needs a higher combined score, and cost also caps the tier on its own.
Scored on 5 axes, measured over the trailing 30 days.

| Axis | Current | Needed | Met | Measures |
| --- | --- | --- | --- | --- |
| width | 2.3 | 5.5 | no | agents running at once |
| depth | 4.2M | 23.3M | no | tokens per session |
| output | 10.0 | 6.0 | yes | agent PRs merged per week |
| sustain | 22 | 24 | no | active days in the last 30 |
| cost | $43.25 | <= $104.48 | yes | USD per merged PR, lower is better |

## Achievements

- **efficient** (level 3 of 3) at $100, earned 2026-09-07
- **ship-it** (level 2 of 4) at 10, earned 2026-09-07
- **two-hands** (level 1 of 3) at 10, earned 2026-09-07
- **whole-task** (level 1 of 3) at 2.5M, earned 2026-09-07

## Milestones

- sessions: 1.0K
- spend: 1.0K
- tokens: 1.00B

## Contributions

- Active days in the last year: 31
- Busiest day: 2026-08-18 at 659.4M tokens

## Models

| Provider | Model | Tokens | Cost |
| --- | --- | --- | --- |
| claude | claude-sonnet-5 | 4.70B | $1992.67 |
| claude | claude-fable-5 | 1.02B | $1652.26 |
| codex | gpt-5.6-sol | 461.7M | $310.99 |
| claude | claude-opus-5 | 305.6M | $330.29 |
| claude | claude-fable-5-1 | 257.8M | $322.73 |
| cursor | cursor-grok-4.5-high | 195.3M | $118.78 |
| cursor | cursor-grok-4.5-high-fast | 149.7M | $203.13 |
| cursor | default | 107.3M | $77.03 |

## Token breakdown

- Uncached input: 59.2M
- Cached input: 7.33B
- Cache write 5m: 52.2M
- Cache write 1h: 109.4M
- Output: 27.7M
- Reasoning output: 6.7M

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