live
weekly refresh
basedagi.org
benchmark evidence

Remote Labor Index

Scale Labs benchmark for economically valuable end-to-end remote work automation.

winner on Remote Labor Index
direct benchmark result, not a broad vertical composite | source row dated 2025-10-27
scored on 2025-10-27 · stale source data (215d)
latest mapped results | top 20
#ModelScoreEvidenceTested
1Anthropic: Claude Sonnet 4.5
Anthropic
48.4
model-only
independent_benchmark
2025-10-27
2OpenAI: GPT-5
Openai
38.9
model-only
independent_benchmark
2025-10-27
what this result means

Scale Labs benchmark for economically valuable end-to-end remote work automation.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on Remote Labor Index. Broad task pages require independent corroboration before naming a general winner.

source record
category: agentic
metric: accuracy
matched models: 2
latest source date: 2025-10-27
direction: higher is better
inspect upstream source ->