LifeSci Diamond (2026-11; 4 November 2026 edition) - Arca Workflow - Partial Credit: leaderboard
Arca’s 4 November 2026 edition regrades 55 regulatory affairs tasks with a revised strict-pass rubric and one GPT-6.1 Sol judge at medium reasoning effort, including OpenAI contestants. The native benchmark version is 2026-11-03-gdp-v6. The historical answer batches include 102 answers refreshed November 4. Ten example tasks are public; 45 are held out and 11 answer keys lack expert review. Arca workflow scores describe requested configurations, with incomplete historical per-step routing. The requested Opus 5 row includes one observed mixed-model outcome. Native CSV mean partial-credit precision is retained; this metric is separate from strict pass.
Metric: Mean partial-credit score (0-100). Source: www.arca.inc. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Arca Run: LifeSci Diamond 2026-11; Fixed) | 87.11 | |
| 2 | GPT-6.1 Terra (Arca Run: LifeSci Diamond 2026-11; Auto) | 80.18 | |
| 3 | Claude Opus 5.5 (Arca Run: LifeSci Diamond 2026-11; Fixed) | 79.4 | |
| 4 | Claude Opus 5 (Arca Run: LifeSci Diamond 2026-11; Fixed) | 77.5 |
Interactive version: theaggregate.ai/benchmark?slug=lifesci-diamond-2026-11-4-november-2026-edition-arca-workflow-partial-credit · How It Works · Data refreshed daily, snapshot 2026-11-06.