AA-Briefcase v1.1
Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT.
Changes only how Elo ratings are fitted. Artificial Analysis says scores shift but the ranking mostly holds, so v1 and v1.1 Elo values do not compare. Part of Intelligence Index v4.3.2 and v5.
- 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 5.5 leads with 1,822
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.
Bars start at 1,400.
- 1 Claude Opus 5.5 1,822
- 2 Claude Sonnet 5.5 1,811
- 3 Kimi K3.1 Pro 1,678
- 4 Grok 4.7 1,657
- 5 Claude Haiku 5.5 1,578
- 6
Step 5 Preview 1,433
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 1,822 | Sep 2026 | Model card | |
| 2 | Claude Sonnet 5.5 | 1,811 | Sep 2026 | Model card | |
| 3 | Kimi K3.1 Pro | 1,678 | Oct 2026 | Model card | |
| 4 | Grok 4.7 | 1,657 | Sep 2026 | Model card | |
| 5 | Claude Haiku 5.5 | 1,578 | Oct 2026 | Model card | |
| 6 | Step 5 Preview | 1,433 | Sep 2026 | Model card |
3 models have held number one since its release in Sep 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 |
|---|---|---|---|
| 24 Oct 2026 | Kimi K3.1 Pro | 1678 | AA-Briefcase v1.1 (Elo-score) |
| 7 Oct 2026 | Claude Haiku 5.5 | 1578 | Knowledge work AA-Briefcase v1.1 |
| 28 Sep 2026 | Claude Sonnet 5.5 | 1811 | Knowledge work AA-Briefcase v1.1 |
| 22 Sep 2026 | Claude Opus 5.5 | 1822 | AA-Briefcase v1.1 |
| 21 Sep 2026 | Grok 4.7 | 1657 | AA Briefcase v1.1 (Multi-hour office work) |
| 20 Sep 2026 | Step 5 Preview | 1433 | AA-Briefcase v1.1 |
3 system cards report it, from 1 lab
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 |
|---|---|---|---|---|
| 7 Oct 2026 | Claude Haiku 5.5 system card | 1578 | AA-Briefcase v1.1, Elo at max effort (medium 1372) (Table 8.1.A) | Capabilities |
| 28 Sep 2026 | Claude Sonnet 5.5 system card | 1811 | AA-Briefcase v1.1 Elo at max effort, run by Artificial Analysis (Table 8.1.A, 8.14.4) | Capabilities |
| 22 Sep 2026 | Claude Opus 5.5 system card | 1822 | AA-Briefcase v1.1 Elo at max effort, run by Artificial Analysis (1780 at xhigh, 1705 at high) (Table 8.1.A, 8.14.4) | 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%