AA-Briefcase
Artificial Analysis knowledge-work evaluation of professional deliverables. Models ranked by Elo.
Scored tasks are private. AA-Briefcase-Lite is an illustrative public scenario. Runs on AA's open Stirrup agent harness (github.com/ArtificialAnalysis/Stirrup).
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Claude Opus 5 leads with 1,720 among models released by Sep 2026
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Sep 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 13 more
Bars start at 800.
- 1 Claude Opus 5 1,720
- 2 Claude Fable 5.1 1,694
- 3 Grok 4.6 1,577
- 4 Kimi K3 1,548
- 5 Claude Sonnet 5 1,393
- 6
Inkling-Small 917
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 1,720 | Jul 2026 | Model card | |
| 2 | Claude Fable 5.1 | 1,694 | Sep 2026 | Model card | |
| 3 | Grok 4.6 | 1,577 | Aug 2026 | Model card | |
| 4 | Kimi K3 | 1,548 | Jul 2026 | Model card | |
| 5 | Claude Sonnet 5 | 1,393 | Jun 2026 | Model card | |
| 6 | Inkling-Small | 917 | Jul 2026 | Model card |
3 models have held number one since its release in Jan 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
4 labs 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 1 Sep 2026 | Claude Fable 5.1 | 1694 | AA-Briefcase |
| 12 Aug 2026 | Grok 4.6 | 1577 | AA-Briefcase |
| 30 Jul 2026 | Inkling-Small | 917 | AA-Briefcase |
| 24 Jul 2026 | Claude Opus 5 | 1720 | AA-Briefcase |
| 16 Jul 2026 | Kimi K3 | 1548 | AA-Briefcase (Elo) |
6 system cards report it, from 4 labs
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.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 1 Sep 2026 | Claude Fable 5.1 system card | 1694 | AA-Briefcase Elo at max effort, run by Artificial Analysis (Table 8.1.A, 8.15.4) | Capabilities |
| 12 Aug 2026 | Grok 4.6 model card | 1577 | AA-Briefcase, Elo, high, Artificial Analysis harness (3.2) | Capabilities |
| 30 Jul 2026 | Inkling-Small model card | 917 | AA-Briefcase (5. Evaluations table) | Capabilities |
| 27 Jul 2026 | Kimi K3 technical report | 1548 | AA-Briefcase (Elo), cited from Artificial Analysis (Table 2) | Capabilities |
| 24 Jul 2026 | Claude Opus 5 system card | 1720 | AA-Briefcase Elo at max effort, run by Artificial Analysis (1693 at xhigh, 1606 at high) (Table 8.1.A, 8.13.5) | Capabilities |
| 30 Jun 2026 | Claude Sonnet 5 system card | 1393 | AA-Briefcase Elo, run by Artificial Analysis (8.11.7) | Capabilities |
Versions
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
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished).
Qwen3.8-Omni-Flash 75.3% - 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%
- SpreadsheetBench In use Real spreadsheet manipulation questions from Excel forums. Output workbook is checked cell-by-cell against reference solutions.
MiniMax-M3 89.3%