Benchmarks / Agentic
Remote Labor Index
Uses the dashboard.safe.ai RLI automation-rate API. Score: automation rate. Collected by Jake Boggs' benchmark dashboard.
Remote Labor Index
Higher is better · best effort per model
full table below
| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Opus 5.5 | max | 21.3% |
| 2 | GPT-6 Astra | max | 20.8% |
| 3 | Fable 5.1 | max | 17.9% |
| 4 | Fable 5 | max | 15.8% |
| 5 | Opus 4.8 | max | 8.3% |
| 6 | GPT-5.5 | xhigh | 6.3% |
| 7 | Gemini 3.8 Flash | max | 5.8% |
| 8 | Gemini 3.7 Flash | max | 5.0% |
| 9 | Opus 4.6 | max | 4.2% |
| 10 | Opus 4.5 | high | 3.8% |
| 11 | GPT-5.2 | xhigh | 2.5% |
| 12 | Sonnet 4.5 | high | 2.1% |
| 13 | Grok 4 | high | 2.1% |
| 14 | GPT-5 | high | 1.7% |
| 15 | Gemini 3 Pro | high | 1.3% |
| 16 | Gemini 2.5 Pro | high | 0.8% |