---
title: "Dagim Shimelis (@dagi)"
description: "Rank #2077 of 2167 on the Superset leaderboard, tier 1."
canonical: https://superset.sh/dagi
last-updated: 2026-10-09
---

# Dagim Shimelis (@dagi)

Rank #2077 of 2167 on the Superset leaderboard, tier 1.

URL: https://superset.sh/dagi

## Standing

- Rank: #2077 of 2167
- Tier: Button pusher
- Tokens: 167.4M all time
- Cost: $122.03 API-equivalent
- Sessions: 422
- Tracking: 2026-08-26 to 2026-10-09

## Bio

> Senior Frontend Web Developer \| Converting caffeine into websites since 2020

## Links

- X: https://x.com/Dagim__Shimelis
- Site: https://dagim.codes

## 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 | 1.0 | 3.1 | no | agents running at once |
| depth | 496.5K | 10.4M | no | tokens per session |
| output | 1.5 | 2.1 | no | agent PRs merged per week |
| sustain | 22 | 17 | yes | active days in the last 30 |
| cost | $10.03 | <= $315.60 | yes | USD per merged PR, lower is better |

## Achievements

- **efficient** (level 3 of 3) at $100, earned 2026-10-09
- **ship-it** (level 2 of 4) at 10, earned 2026-10-09

## Milestones

- sessions: 100
- spend: 100
- tokens: 100.0M

## Contributions

- Active days in the last year: 29
- Busiest day: 2026-10-08 at 28.3M tokens

## Models

| Provider | Model | Tokens | Cost |
| --- | --- | --- | --- |
| codex | gpt-6-sol | 104.9M | $31.13 |
| codex | gpt-6-astra | 39.0M | $74.24 |
| codex | codex-auto-review | 8.8M | $0.32 |
| claude | claude-haiku-4-5-20251001 | 7.2M | $6.47 |
| claude | claude-opus-5 | 7.1M | $8.73 |
| codex | gpt-5.6-sol | 300.5K | $1.12 |
| codex | gpt-5.6-luna | 116.6K | $0.01 |
| codex | unknown | 0 | $0.00 |

## Token breakdown

- Uncached input: 9.8M
- Cached input: 154.0M
- Cache write 5m: 0
- Cache write 1h: 2.8M
- Output: 817.3K
- Reasoning output: 463.6K

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