AA-Briefcase v1.1, rubric pass rate (AA-Briefcase (rubric))
We show this table for reference; we do not rank on it.
The rubric pass rate on Artificial Analysis's AA-Briefcase v1.1 knowledge-work benchmark, alongside its Elo headline.
Benchmark score on AA-Briefcase (rubric) — November 11, 2026
We compile the AA-Briefcase (rubric) rows from provider self-reports. Claude Fable 5.2 leads the table at 66.1%, followed by Gemini 4 Carbon (61.8%) and Claude Fable 5.1 (61.5%). We do not use these results to rank models overall.
Claude Fable 5.2
Anthropic
Gemini 4 Carbon
Claude Fable 5.1
Anthropic
5 modelsAgenticCurrentDisplay onlyUpdated November 11, 2026
Benchmark score table (5 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Fable 5.2Anthropic | 66.1% | Not reported | Closed |
| 2 | Gemini 4 CarbonGoogle | 61.8% | Not reported | Closed |
| 3 | Claude Fable 5.1Anthropic | 61.5% | Not reported | Closed |
| 4 | Claude Opus 5.5Anthropic | 61.2% | Not reported | Closed |
| 5 | GPT-6 AstraOpenAI | 52.0% | Not reported | Closed |
Among the reported AA-Briefcase (rubric) rows, Claude Fable 5.2 is first at 66.1%. The third row is 4.6 points behind. The broader top-10 range is 14.1 points, so the table still separates the published systems.
5 models have been evaluated on AA-Briefcase (rubric). The benchmark falls in the Agentic category. AA-Briefcase (rubric) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About AA-Briefcase (rubric)
Year
2026
Tasks
Professional knowledge-work briefs
Format
Rubric pass rate
Difficulty
Professional knowledge work
AA-Briefcase's headline is an Elo rating, stored on the AA-Briefcase Elo page. Anthropic's Claude Fable 5.2 launch also reports the rubric pass rate measured by Artificial Analysis, which BenchLM keeps on this display-only lane.
Freshness and provenance
Version
AA-Briefcase (rubric) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does AA-Briefcase (rubric) measure?
The rubric pass rate on Artificial Analysis's AA-Briefcase v1.1 knowledge-work benchmark, alongside its Elo headline.
Which model scores highest on AA-Briefcase (rubric)?
Claude Fable 5.2 by Anthropic currently leads with a score of 66.1% on AA-Briefcase (rubric).
How many models are evaluated on AA-Briefcase (rubric)?
5 AI models have published results on AA-Briefcase (rubric) in the BenchLM catalog.
Compare top models on AA-Briefcase (rubric)
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.