Remote Labor Index (RLI) (Remote Labor Index)
We show this table for reference; we do not rank on it.
Scale AI and the Center for AI Safety's benchmark of 240 real paid freelance projects; the automation rate is the share of projects whose deliverable a client would accept.
Benchmark score on Remote Labor Index — November 10, 2026
We compile the Remote Labor Index rows from provider self-reports. Claude Fable 5.2 leads the table at 41.3%, followed by Claude Opus 5.5 (21.3%) and GPT-6 Astra (20.8%). We do not use these results to rank models overall.
Claude Fable 5.2
Anthropic
Claude Opus 5.5
Anthropic
GPT-6 Astra
OpenAI
4 modelsAgenticCurrentDisplay onlyUpdated November 10, 2026
Benchmark score table (4 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Fable 5.2Anthropic | 41.3% | Not reported | Closed |
| 2 | Claude Opus 5.5Anthropic | 21.3% | Not reported | Closed |
| 3 | GPT-6 AstraOpenAI | 20.8% | Not reported | Closed |
| 4 | Claude Fable 5.1Anthropic | 17.9% | Not reported | Closed |
Among the reported Remote Labor Index rows, Claude Fable 5.2 is first at 41.3%. The third row is 20.5 points behind. The broader top-10 range is 23.4 points, so the table still separates the published systems.
4 models have been evaluated on Remote Labor Index. The benchmark falls in the Agentic category. Remote Labor Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Remote Labor Index
Year
2025
Tasks
240 freelance projects
Format
Automation rate (%)
Difficulty
End-to-end remote work
Scale AI ran the Claude models at default high effort with a 200K-token context window and a 32K-token response limit. BenchLM first stored RLI automation rates from Anthropic's Claude Fable 5.2 system card and keeps the lane display-only.
Freshness and provenance
Version
Remote Labor Index 2025
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Remote Labor Index measure?
Scale AI and the Center for AI Safety's benchmark of 240 real paid freelance projects; the automation rate is the share of projects whose deliverable a client would accept.
Which model scores highest on Remote Labor Index?
Claude Fable 5.2 by Anthropic currently leads with a score of 41.3% on Remote Labor Index.
How many models are evaluated on Remote Labor Index?
4 AI models have published results on Remote Labor Index in the BenchLM catalog.
Compare top models on Remote Labor Index
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.