BusinessCaseBench: leaderboard
Case-grounded professional knowledge work across the business disciplines - the judgement calls that benchmarks built on recall, narrow QA, maths and coding do not reach.
Metric: Score (%). Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 88.4 | #90 |
| 2 | Claude Fable 5 | 88 | #16 |
| 3 | GPT-5.4 | 87.2 | #79 |
| 4 | GPT-5 | 84.9 | #98 |
| 5 | Gemini 3 Flash (Preview) | 81.6 | #82 |
| 6 | GPT-4.1 | 80.7 | #248 |
| 7 | GPT-4 Turbo | 63.9 | #404 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=businesscasebench · How It Works · Data refreshed daily, snapshot 2026-10-20.