SShogo Bench

Remote Labor Index

Real paid freelance projects; share completed to a standard a client would accept.

Agent Index weight
5%
in the Knowledge-work agents pillar
Models tested
18
from the benchmark’s leaderboard and reports
Normalised for the index
0 → 0, 1 → 100
Official site

Results

#ModelScoreNormalisedHarnessCost/taskDate
1Claude Fable 5.2 Supported
Anthropic
41.3%source——
2Claude Opus 5.5 Supported
Anthropic
21.3%source——
3GPT-6 Astra Supported
OpenAI
20.8%source——
4Claude Fable 5.1 Supported
Anthropic
17.9%source——
5Gemini 4 Argon Supported
Google
17.1%source——
6Claude Fable 5 Supported
Anthropic
16.1%source——
7DeepSeek V4.1 Flash Estimated
DeepSeek
9.6%source——
8Claude Opus 4.8 Supported
Anthropic
8.3%source——
9GPT-5.5 Supported
OpenAI
6.3%source——
10Gemini 3.8 Flash Supported
Google
5.8%source——
11Gemini 3.7 Flash Estimated
Google
5.0%source——
12Claude Opus 4.6 Supported
Anthropic
4.2%source——
13Claude Opus 4.5 (latest) Supported
Anthropic
3.8%source——
14GPT-5.2 Supported
OpenAI
2.5%source——
15Claude Sonnet 4.5 (latest) Supported
Anthropic
2.1%source——
16GPT-5 Supported
OpenAI
1.7%source——
17Gemini 3 Pro Preview Supported
Google
1.3%source——
18Gemini 2.5 Pro Supported
Google
0.8%source——

For models without a Remote Labor Index result, the index estimates one from Epoch’s Capabilities Index using a logistic fit on 18 models (residual SD 0.38 on the logit scale). Estimates are labelled and widen the model’s range.