Benchmarks / Remote Labor Index

Reported by Remote Labor Index

Remote Labor Index

Share of 240 real paid freelance projects (design, software, data, architecture and more) an agent delivers at a standard a client would accept.

Last updated 1 Oct 2026

Results dated
1 Oct 2026
Results
14 configurations of 13 models
Unit
% of projects
Licence
Published with permission (Scale AI and the Center for AI Safety results via Epoch AI)

Projects done to client standard:

13 results · % of projects, higher is better. Choose a model to highlight it.Clear highlight

  1. 1 GPT-6 AstraOpenAI 20.8%
  2. 2 Claude Fable 5.1Anthropic 17.9%
  3. 3 Claude Fable 5Anthropic 16.1%
  4. 4 Claude Opus 4.8Anthropic 8.3%
  5. 5 GPT-5.5OpenAI 6.3%
  6. 6 Gemini 3.7 FlashGoogle 5.0%
  7. 7 Claude Opus 4.6Anthropic 4.2%
  8. 8 Claude Opus 4.5Anthropic 3.8%
  9. 9 GPT-5.2 (medium reasoning)OpenAI 2.5%
  10. 10 Claude Sonnet 4.5Anthropic 2.1%
  11. 11 GPT-5OpenAI 1.7%
  12. 12 Gemini 3 Pro PreviewGoogle 1.3%
  13. 13 Gemini 2.5 Pro Preview (06-05)Google 0.8%

Full results

Remote Labor Index: projects done to client standard, % of projects, higher is better
#ModelProjects done to client standard
% of projects, higher is better		Price
$ per million tokens, in / out
1 GPT-6 AstraOpenAI
20.8%
$10 / $50
2 Claude Fable 5.1Anthropic
17.9%
$10 / $50
3 Claude Fable 5Anthropic
16.1%
$10 / $50
4 Claude Opus 4.8Anthropic
8.3%
$5 / $25
5 GPT-5.5OpenAI
6.3%
$5 / $30
6 Gemini 3.7 FlashGoogle
5.0%
$1.50 / $7.50
7 Claude Opus 4.6Anthropic
4.2%
$5 / $25
8 Claude Opus 4.5Anthropic
3.8%
$5 / $25
9 GPT-5.2 (medium reasoning)OpenAI · best of 2 settings
2.5%
$1.75 / $14
10 Claude Sonnet 4.5Anthropic
2.1%
$3 / $15
11 GPT-5OpenAI
1.7%
$1.25 / $10
12 Gemini 3 Pro PreviewGoogle
1.3%
–
13 Gemini 2.5 Pro Preview (06-05)Google
0.8%
$1.25 / $10

Swipe the table sideways for more columns.

Ranks follow the score as shown, so equal numbers share a rank. Each model is shown at its best setting; show every setting. Results as published by Remote Labor Index; we do not re-run them.

Progress over time

Projects done to client standard, plotted at each model's release date, higher is better. Each model counts once, at its best setting. Scores are today's, not launch day's; 1 model without a known release date is left off. Hover or tap a mark for its model.

Best score so far

Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.

0%5%10%15%20%25% Oct 20252026AprJulOct GPT-5Claude Sonnet 4.5Claude Opus 4.5Claude Opus 4.6GPT-5.5Claude Opus 4.8Claude Fable 5Claude Fable 5.1GPT-6 Astra

Best score by lab

Each lab's best so far, stepping whenever one of its releases beats its own earlier models.

OpenAIAnthropicGoogle

0%5%10%15%20%25% Oct 20252026AprJulOct OpenAIAnthropicGoogle

What it measures

Share of 240 real paid freelance projects (design, software, data, architecture and more) an agent delivers at a standard a client would accept.

What it does not measure

Not speed or cost; a small set of projects, so a few points either way are noise.

Source

Remote Labor Index · Methodology

1 result from Remote Labor Index not ranked here · show why

We rank a result only when we can tie it to a specific model you can use. These are left out:

  • Listed twice by the source: 1

Scale AI and the Center for AI Safety; collected by Epoch AI. Licence: Published with permission (Scale AI and the Center for AI Safety results via Epoch AI).