---
title: "haruto (@haruto)"
description: "Rank #936 of 1119 on the Superset leaderboard, tier 1."
canonical: https://superset.sh/haruto
last-updated: 2026-09-07
---

# haruto (@haruto)

Rank #936 of 1119 on the Superset leaderboard, tier 1.

URL: https://superset.sh/haruto

## Standing

- Rank: #936 of 1119
- Tier: Button pusher
- Tokens: 840.3M all time
- Cost: $909.63 API-equivalent
- Sessions: 145
- Tracking: 2026-08-09 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 | 1.0 | 3.1 | no | agents running at once |
| depth | 5.0M | 10.4M | no | tokens per session |
| output | 1.0 | 2.1 | no | agent PRs merged per week |
| sustain | 19 | 17 | yes | active days in the last 30 |
| cost | $151.60 | <= $315.60 | yes | USD per merged PR, lower is better |

## Achievements

- **efficient** (level 2 of 3) at $300, earned 2026-09-07
- **ship-it** (level 1 of 4) at 1, earned 2026-09-07
- **whole-task** (level 1 of 3) at 2.5M, earned 2026-09-07

## Milestones

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

## Contributions

- Active days in the last year: 19
- Busiest day: 2026-09-06 at 275.6M tokens

## Models

| Provider | Model | Tokens | Cost |
| --- | --- | --- | --- |
| claude | claude-opus-5 | 295.4M | $250.46 |
| claude | claude-fable-5 | 220.7M | $433.76 |
| cursor | GPT-5.6 Sol (Auto Intelligence) | 107.6M | $53.69 |
| claude | claude-sonnet-5 | 76.6M | $26.99 |
| cursor | claude-opus-5-thinking-high | 41.2M | $34.38 |
| cursor | gpt-5.6-sol-high | 25.5M | $49.09 |
| cursor | GPT-5.6 Sol (Auto Balanced) | 24.2M | $12.67 |
| cursor | Claude Opus 5 (Auto Intelligence) | 11.5M | $17.10 |

## Token breakdown

- Uncached input: 3.3M
- Cached input: 802.0M
- Cache write 5m: 15.5M
- Cache write 1h: 16.1M
- Output: 3.3M
- Reasoning output: 392.8K

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