Benchmark Almanac

Remote Labor Index

Claude Fable 5.2 41.3% leads since November 2026
Claude Fable 5.2 41.3% leads since November 2026
In use

Agents complete real paid remote freelance projects from many sectors. Reviewers judge whether each deliverable would be accepted as commissioned work, giving an automation rate.

The best agent automated only 2.5% of projects at launch. Only a 10 task public set is released.

Released
October 2025
Kind
Tasks from real jobs
Level
Expert
Scored
Graded by people
Answers
Open-ended
Tasks
Public, plus a private test set
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026

In the authors’ words

AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5%. These results help ground discussions of AI automation in empirical evidence, setting a common basis for tracking AI impacts and enabling stakeholders to proactively navigate AI-driven labor automation.

Abstract of Remote Labor Index: Measuring AI Automation of Remote Work (arXiv:2510.26787, CC0)
22
Entries on its own leaderboard, 19 models we track
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab

Claude Fable 5.2 leads with 41.3%

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

Claude Fable 5.2 leads with 41.3%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

22 entries. Scroll sideways for the rest.

  1. 41.3 Claude Fable 5.2
  2. 21.3 Claude Opus 5.5
  3. 20.8 GPT-6 Astra
  4. 17.9 Claude Fable 5.1
  5. 17.1 Gemini 4 Argon
  6. 15.8 Claude Fable 5
  7. 9.58 DeepSeek V4.1 Flash
  8. 8.33 Claude Opus 4.8
  9. 6.25 GPT-5.5
  10. 5.83 Gemini 3.8 Flash
  11. 5.00 Gemini 3.7 Flash
  12. 4.17 Claude Opus 4.6
  13. 3.75 Claude Opus 4.5
  14. 2.92 Manus_1.6
  15. 2.50 Manus 1.0
  16. 2.50 Manus 1.5
  17. 2.50 GPT-5.2
  18. 2.08 Claude Sonnet 4.5
  19. 1.67 GPT-5
  20. 1.25 ChatGPT agent
  21. 1.25 Gemini 3 Pro
  22. 0.83 Gemini 2.5 Pro
  1. 1 Claude Fable 5.2 41.3%
  2. 2 Claude Opus 5.5 21.3%
  3. 3 GPT-6 Astra 20.8%
  4. 4 Claude Fable 5.1 17.9%
  5. 5 Gemini 4 Argon 17.1%
  6. 6 Claude Fable 5 15.8%
  7. 7 DeepSeek V4.1 Flash 9.58%
  8. 8 Claude Opus 4.8 8.33%
  9. 9 GPT-5.5 6.25%
  10. 10 Gemini 3.8 Flash 5.83%
  11. 11 Gemini 3.7 Flash 5.00%
  12. 12 Claude Opus 4.6 4.17%
  13. 13 Claude Opus 4.5 thinking 3.75%
  14. 14 Manus_1.6 max 2.92%
  15. 15 Manus 1.0 2.50%
  16. 16 Manus 1.5 2.50%
  17. 17 GPT-5.2 medium 2.50%
  18. 18 Claude Sonnet 4.5 2.08%
  19. 19 GPT-5 1.67%
  20. 20 ChatGPT agent 1.25%
  21. 21 Gemini 3 Pro 1.25%
  22. 22 Gemini 2.5 Pro Jun 2025 0.83%

Source: Official Remote Labor Index leaderboard

19 models. Scroll sideways for the rest.

  1. 41.3 Claude Fable 5.2
  2. 21.3 Claude Opus 5.5
  3. 20.8 GPT-6 Astra
  4. 17.9 Claude Fable 5.1
  5. 17.1 Gemini 4 Argon
  6. 15.8 Claude Fable 5
  7. 9.58 DeepSeek V4.1 Flash
  8. 8.33 Claude Opus 4.8
  9. 6.25 GPT-5.5
  10. 5.83 Gemini 3.8 Flash
  11. 5.00 Gemini 3.7 Flash
  12. 4.17 Claude Opus 4.6
  13. 3.75 Claude Opus 4.5
  14. 2.50 GPT-5.2
  15. 2.08 Claude Sonnet 4.5
  16. 1.67 GPT-5
  17. 1.25 ChatGPT agent
  18. 1.25 Gemini 3 Pro
  19. 0.83 Gemini 2.5 Pro
  1. 1 Claude Fable 5.2 41.3%
  2. 2 Claude Opus 5.5 21.3%
  3. 3 GPT-6 Astra 20.8%
  4. 4 Claude Fable 5.1 17.9%
  5. 5 Gemini 4 Argon 17.1%
  6. 6 Claude Fable 5 15.8%
  7. 7 DeepSeek V4.1 Flash 9.58%
  8. 8 Claude Opus 4.8 8.33%
  9. 9 GPT-5.5 6.25%
  10. 10 Gemini 3.8 Flash 5.83%
  11. 11 Gemini 3.7 Flash 5.00%
  12. 12 Claude Opus 4.6 4.17%
  13. 13 Claude Opus 4.5 thinking 3.75%
  14. 14 GPT-5.2 medium 2.50%
  15. 15 Claude Sonnet 4.5 2.08%
  16. 16 GPT-5 1.67%
  17. 17 ChatGPT agent 1.25%
  18. 18 Gemini 3 Pro 1.25%
  19. 19 Gemini 2.5 Pro Jun 2025 0.83%

Sources: Labs’ model cards and official Remote Labor Index leaderboard

#EntryScoreSettingDateSource
1 Claude Fable 5.2 41.3% Nov 2026 Official leaderboard
2 Claude Opus 5.5 21.3% Sep 2026 Official leaderboard
3 GPT-6 Astra 20.8% Sep 2026 Official leaderboard
4 Claude Fable 5.1 17.9% Sep 2026 Official leaderboard
5 Gemini 4 Argon 17.1% Sep 2026 Official leaderboard
6 Claude Fable 5 15.8% Jun 2026 Official leaderboard
7 DeepSeek V4.1 Flash 9.58% Sep 2026 Official leaderboard
8 Claude Opus 4.8 8.33% May 2026 Official leaderboard
9 GPT-5.5 6.25% Codex Apr 2026 Official leaderboard
10 Gemini 3.8 Flash 5.83% Sep 2026 Official leaderboard
11 Gemini 3.7 Flash 5.00% Aug 2026 Official leaderboard
12 Claude Opus 4.6 4.17% Cowork Feb 2026 Official leaderboard
13 Claude Opus 4.5 3.75% thinking Nov 2025 Official leaderboard
14 Manus_1.6 2.92% max Official leaderboard
15 Manus 1.0 2.50% Official leaderboard
16 Manus 1.5 2.50% Official leaderboard
17 GPT-5.2 2.50% medium Dec 2025 Official leaderboard
18 Claude Sonnet 4.5 2.08% Sep 2025 Official leaderboard
19 GPT-5 1.67% Aug 2025 Official leaderboard
20 ChatGPT agent 1.25% Jul 2025 Official leaderboard
21 Gemini 3 Pro 1.25% Nov 2025 Official leaderboard
22 Gemini 2.5 Pro Jun 2025 0.83% Jun 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5.2 41.3% Nov 2026 Lab model card
2 Claude Opus 5.5 21.3% Sep 2026 Official leaderboard
3 GPT-6 Astra 20.8% Sep 2026 Official leaderboard
4 Claude Fable 5.1 17.9% Sep 2026 Official leaderboard
5 Gemini 4 Argon 17.1% Sep 2026 Official leaderboard
6 Claude Fable 5 15.8% Jun 2026 Official leaderboard
7 DeepSeek V4.1 Flash 9.58% Sep 2026 Official leaderboard
8 Claude Opus 4.8 8.33% May 2026 Official leaderboard
9 GPT-5.5 6.25% Codex Apr 2026 Official leaderboard
10 Gemini 3.8 Flash 5.83% Sep 2026 Official leaderboard
11 Gemini 3.7 Flash 5.00% Aug 2026 Official leaderboard
12 Claude Opus 4.6 4.17% Cowork Feb 2026 Official leaderboard
13 Claude Opus 4.5 3.75% thinking Nov 2025 Official leaderboard
14 GPT-5.2 2.50% medium Dec 2025 Official leaderboard
15 Claude Sonnet 4.5 2.08% Sep 2025 Official leaderboard
16 GPT-5 1.67% Aug 2025 Official leaderboard
17 ChatGPT agent 1.25% Jul 2025 Official leaderboard
18 Gemini 3 Pro 1.25% Nov 2025 Official leaderboard
19 Gemini 2.5 Pro Jun 2025 0.83% Jun 2025 Official leaderboard

Labs report scores for 1 model in their cards. Switch the scores above to rank them together.

10 models have held number one on the official leaderboard since its release in October 2025 10 models have held number one with claims included since its release in October 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic OpenAI
Own leaderboard 10 leaders
Claude Fable 5.2 41.3%

Source: Official Remote Labor Index leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Claude Fable 5.2 Claude Opus 5.5 Claude Fable 5 Claude Opus 4.8 Claude Opus 4.6 Claude Sonnet 4.5 Gemini 2.5 Pro 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Claude Fable 5.2 Claude Opus 5.5

Sources: Official Remote Labor Index leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Anthropic
DateLaunch postScoreAs the post writes it
Nov 9, 2026 Claude Fable 5.2 41.3 Knowledge work Remote Labor Index (RLI), High effort (launch table and Table 8.1.A)

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Nov 9, 2026 Claude Fable 5.2 system card 41.3 Remote Labor Index, automation rate, 99 of 240 projects, default High effort, 200k context, 32k output tokens per response, independently run by Scale AI (Table 8.1.A and Section 8.14.7) Capabilities

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Claude Fable 5.2 41.3% Knowledge work Remote Labor Index (RLI), High effort (launch table and Table 8.1.A) 41.3% Leaderboard Same

More in Economic work

All 97 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
  • OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%