# Scale Labs Remote Labor Index (Remote Labor Index)

> A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

Canonical page: https://benchlm.ai/benchmarks/scale-rli

- Category: [Agentic](/agentic)
- Last updated: September 29, 2026 snapshot

## About Remote Labor Index

- Year: 2026
- Tasks: 18 published rows
- Format: Published Scale leaderboard score
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/rli)

BenchLM mirrors 18 published rows from the Remote Labor Index public table captured on September 29, 2026 snapshot.

Remote Labor Index is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (18 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 20.83% |
| 2 | [Fable 5.1](https://labs.scale.com/leaderboard/rli) | Anthropic | 17.92% |
| 3 | [Fable 5](https://labs.scale.com/leaderboard/rli) | Anthropic | 15.80% |
| 4 | [Opus 4.8](https://labs.scale.com/leaderboard/rli) | Anthropic | 8.33% |
| 5 | [Codex GPT 5.5](https://labs.scale.com/leaderboard/rli) | OpenAI | 6.25% |
| 6 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | 5.00% |
| 7 | [claude-opus-4-6 (CoWork)](https://labs.scale.com/leaderboard/rli) | Anthropic | 4.17% |
| 8 | [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) | Anthropic | 3.75% |
| 9 | [Manus_1.6 (Max)](https://labs.scale.com/leaderboard/rli) | Deepseek | 2.92% |
| 10 | [gpt-5.2-2025-12-11 (medium)](https://labs.scale.com/leaderboard/rli) | OpenAI | 2.50% |
| 11 | [Manus 1.5](https://labs.scale.com/leaderboard/rli) | Deepseek | 2.50% |
| 12 | [Manus 1.0](https://labs.scale.com/leaderboard/rli) | Deepseek | 2.50% |
| 13 | [gpt-5.2-2025-12-11 (default)](https://labs.scale.com/leaderboard/rli) | OpenAI | 2.08% |
| 14 | [claude-4-5-Sonnet](https://labs.scale.com/leaderboard/rli) | Anthropic | 2.08% |
| 15 | [gpt-5-2025-08-07](https://labs.scale.com/leaderboard/rli) | OpenAI | 1.67% |
| 16 | [gemini-3-pro-preview](https://labs.scale.com/leaderboard/rli) | Google | 1.25% |
| 17 | [ChatGPT agent](https://labs.scale.com/leaderboard/rli) | OpenAI | 1.25% |
| 18 | [gemini-2.5-pro-preview-06-05](https://labs.scale.com/leaderboard/rli) | Google | 0.83% |

## FAQ

### What does Remote Labor Index measure?

A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

### Which model leads the published Remote Labor Index snapshot?

GPT-6 Astra currently leads the published Remote Labor Index snapshot with a score of 20.83%.

### How many models are evaluated on Remote Labor Index?

The September 29, 2026 snapshot contains 18 AI models.

### Does Remote Labor Index affect BenchLM's overall score?

Not directly. Remote Labor Index is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.