---
title: "Daniel Golshani (@daniel-golshani)"
description: "Rank #1717 of 2200 on the Superset leaderboard, tier 1."
canonical: https://superset.sh/daniel-golshani
last-updated: 2026-10-11
---

# Daniel Golshani (@daniel-golshani)

Rank #1717 of 2200 on the Superset leaderboard, tier 1.

URL: https://superset.sh/daniel-golshani

## Standing

- Rank: #1717 of 2200
- Tier: Button pusher
- Tokens: 2.36B all time
- Cost: $1924.68 API-equivalent
- Sessions: 287
- Tracking: 2026-09-14 to 2026-10-11

## 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 | 2.0 | 3.1 | no | agents running at once |
| depth | 7.3M | 10.4M | no | tokens per session |
| output | 3.5 | 2.1 | yes | agent PRs merged per week |
| sustain | 18 | 17 | yes | active days in the last 30 |
| cost | $106.93 | <= $315.60 | yes | USD per merged PR, lower is better |

## Achievements

- **efficient** (level 2 of 3) at $300, earned 2026-10-11
- **ship-it** (level 2 of 4) at 10, earned 2026-10-11
- **two-hands** (level 1 of 3) at 10, earned 2026-10-11
- **whole-task** (level 1 of 3) at 2.5M, earned 2026-10-11

## Milestones

- sessions: 100
- spend: 1.0K
- tokens: 1.00B

## Contributions

- Active days in the last year: 18
- Busiest day: 2026-09-30 at 422.5M tokens

## Models

| Provider | Model | Tokens | Cost |
| --- | --- | --- | --- |
| claude | claude-fable-5-1 | 576.0M | $699.14 |
| claude | claude-opus-5-5 | 571.7M | $528.65 |
| claude | claude-opus-5 | 498.7M | $404.93 |
| claude | claude-sonnet-5 | 335.8M | $118.31 |
| codex | gpt-5.6-sol | 115.5M | $61.13 |
| codex | gpt-6-sol | 105.0M | $2.67 |
| codex | gpt-6-astra | 54.1M | $79.18 |
| codex | gpt-5.6-terra | 52.4M | $14.41 |

## Token breakdown

- Uncached input: 8.4M
- Cached input: 2.27B
- Cache write 5m: 12.1M
- Cache write 1h: 59.6M
- Output: 8.5M
- Reasoning output: 3.2M

Published voluntarily by the account holder. Source: https://superset.sh/daniel-golshani