LLM Stats (LifeSci Diamond (2026-11); 4 November 2026 edition): 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. Eighteen plain APIs use the shared Vercel AI Gateway reference harness, Exa search snippets and up to 40 model steps. Effective reasoning, temperature and token settings are unrecorded provider defaults; gateway aliases are not immutable snapshots. The relay scores are checked against the native CSV. Strict pass is separate from partial credit and Arca workflow results.
Metric: Strict pass rate (%). Source: llm-stats.com. Saturation forecast: Around 2029. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 20 | #5 |
| 2 | GPT-6.1 Sol | 14.5 | #6 |
| 3 | GPT-6.1 Terra | 9.1 | #15 |
| 4 | Muse Wonder | 9.1 | #18 |
| 5 | GPT-5.6 Sol | 5.5 | #22 |
| 6 | Claude Fable 5 | 3.6 | #20 |
| 7 | Claude Opus 5.5 | 3.6 | #3 |
| 8 | Grok 4.6 | 3.6 | #30 |
| 9 | Kimi K3 | 1.8 | #35 |
| 10 | Claude Opus 5 | 1.8 | #16 |
| 11 | Claude Sonnet 5 | 1.8 | #66 |
| 12 | GPT-5.6 Terra | 1.8 | #41 |
| 13 | Gemini 3.7 Flash | 1.8 | #24 |
| 14 | Claude Fable 5.1 | 1.8 | #10 |
| 15 | Gemini 3.1 Pro (Preview) | 0 | #65 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-lifesci-diamond-2026-11-4-november-2026-edition · How It Works · Data refreshed daily, snapshot 2026-11-06.