---
title: "Frederik Brammer (@frederik)"
description: "Rank #55 of 1120 on the Superset leaderboard, tier 1."
canonical: https://superset.sh/frederik
last-updated: 2026-09-07
---

# Frederik Brammer (@frederik)

Rank #55 of 1120 on the Superset leaderboard, tier 1.

URL: https://superset.sh/frederik

## Standing

- Rank: #55 of 1120
- Tier: Button pusher
- Tokens: 38.29B all time
- Cost: $22619.63 API-equivalent
- Sessions: 1114
- Tracking: 2026-08-07 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. Operator 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 | 3.0 | 3.1 | no | agents running at once |
| depth | 28.8M | 10.4M | yes | tokens per session |
| output | 4.5 | 2.1 | yes | agent PRs merged per week |
| sustain | 28 | 17 | yes | active days in the last 30 |
| cost | $915.28 | <= $315.60 | no | USD per merged PR, lower is better |

## Achievements

- **plant-floor** (level 1 of 3) at 10, 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 2 of 3) at 10.0M, earned 2026-09-07

## Milestones

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

## Contributions

- Active days in the last year: 30
- Busiest day: 2026-08-12 at 3.28B tokens

## Models

| Provider | Model | Tokens | Cost |
| --- | --- | --- | --- |
| codex | gpt-5.6-sol | 33.91B | $17939.06 |
| codex | gpt-6-astra | 1.67B | $2505.65 |
| claude | claude-opus-5 | 1.38B | $1100.65 |
| claude | claude-fable-5 | 530.4M | $866.79 |
| codex | gpt-5.5 | 294.7M | $60.31 |
| codex | gpt-5.6-terra | 272.5M | $74.94 |
| grok | grok-4.6 | 189.0M | $61.60 |
| claude | claude-sonnet-5 | 31.7M | $9.34 |

## Token breakdown

- Uncached input: 846.8M
- Cached input: 37.29B
- Cache write 5m: 27.9M
- Cache write 1h: 23.1M
- Output: 101.4M
- Reasoning output: 33.5M

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