AI Professions Prompt Benchmark
Models draft everyday work documents from fictional inputs: 100 prompts for tasks in 10 professions, such as accounting, law, healthcare administration and real estate, plus Excel and Microsoft 365, in English, Spanish, French and Portuguese. A judge model from another family checks 5 pass or fail criteria per prompt, fixed before any model ran.
Kept by its makers, who grade GPT-6 Astra with Claude Opus 5.5 and every other model with GPT-6 Astra. Only the models that share that judge are on the board here. Submitted by the makers in issue 10.
- Made by
- AI Professions
- Released
- October 2026
- Kind
- Tasks from real jobs
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Economics and business, Law, Health sciences, Civil engineering, Arts
- Language
- English, Spanish, French, Portuguese
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Occupations
- Management, Business and financial operations, Architecture and engineering, Legal, Arts, design, entertainment, sports and media, Healthcare practitioners and technical, Sales
- In views
- Biology and medicine, Law and finance
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 19th, 2026
Claude Opus 5.5 leads with 85.9% among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 13 more
- 1 Claude Opus 5.5 85.9%
- 2
Gemini 4 Argon medium 84.9%
- 3 Claude Fable 5.1 82.9%
- 4 Claude Sonnet 5 79.6%
Source: Official AI Professions Prompt Benchmark leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 85.9% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 2 | | 84.9% | medium | Sep 2026 | Oct 2026 | Official leaderboard |
| 3 | Claude Fable 5.1 | 82.9% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 4 | Claude Sonnet 5 | 79.6% | Jun 2026 | Oct 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AI Professions Prompt Benchmark leaderboard
Claude Opus 5.5 on the official leaderboard passed 85% in September 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AI Professions Prompt Benchmark leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More 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
- Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
- 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%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (4 entries).
- Note Models scored Only 4 models we track.
- Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
- Pass Frontier models 3 of the top 10 have a score, led by Claude Opus 5.5 (#5).
- Note Headroom Saturated. The best is 85.9%, past 85% since September 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on aiprofessions.ai: 4 rows for models we track at the last read.
- Pass Last read November 19th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.