Remote Labor Index

Real paid freelance projects; the share an AI agent completes to a client-acceptable standard.

CategoryAgents
MetricAccuracy
SourceEpoch AI (evaluator)
LicenseCC BY 4.0
Benchmark pagewww.remotelabor.ai
StatusScored
Weight1.0 within Agents
FitDiscrimination 1.15, noise 0.38

Results

#ModelProviderResultDate
1 Claude Fable 5.2 Anthropic 41.3% 2026-11-11
2 Claude Opus 5.5 Anthropic 21.3% 2026-11-11
3 GPT-6 Astra OpenAI 20.8% 2026-11-11
4 Claude Fable 5.1 Anthropic 17.9% 2026-11-11
5 Gemini 4 Argon Google 17.1% 2026-11-11
6 Claude Fable 5 Anthropic 16.1% 2026-11-11
7 Claude Opus 4.8 Anthropic 8.3% 2026-11-11
8 GPT-5.5 OpenAI 6.3% 2026-11-11
9 Gemini 3.8 Flash Google 5.8% 2026-11-11
10 Gemini 3.7 Flash Google 5.0% 2026-11-11
11 Claude Opus 4.6 Anthropic 4.2% 2026-11-11
12 Claude Opus 4.5 Anthropic 3.8% 2026-11-11
13 GPT-5.2 Medium OpenAI 2.5% 2026-11-11
14 Claude Sonnet 4.5 Anthropic 2.1% 2026-11-11
15 GPT-5.2 OpenAI 2.1% 2026-11-11
16 GPT-5 OpenAI 1.7% 2026-11-11
17 Gemini 3 Pro Preview Google 1.3% 2026-11-11
18 Gemini 2.5 Pro Preview 06-05 Google 0.8% 2026-11-11