The AI arena is free today

Open Superagent

LifeSci Diamond (2026-11)

PaperImplementation

Progress Over Time

Interactive timeline showing model performance evolution on LifeSci Diamond (2026-11)

State-of-the-art frontier
Open
Proprietary

LifeSci Diamond (2026-11) Leaderboard

18 models
ContextCostLicense
1—1.1M$10.00 / $50.00
2—1.1M$2.00 / $10.00
3—1.0M$4.00 / $20.00
3—1.1M$1.00 / $5.00
5—1.1M$5.00 / $30.00
6—1.0M$4.00 / $20.00
6—1.0M$10.00 / $50.00
6—500K$2.00 / $6.00
9—1.0M$10.00 / $50.00
9—1.0M$0.75 / $3.75
9—1.1M$2.00 / $12.00
9
Anthropic
Anthropic
—1.0M$5.00 / $25.00
9
Moonshot AI
Moonshot AI
2.8T1.0M$2.85 / $14.25
9—1.0M$2.00 / $10.00
15—1.0M$2.00 / $12.00
15—1.0M$2.00 / $10.00
15—1.0M$0.10 / $0.20
15—1.0M$5.00 / $25.00
Notice missing or incorrect data?
About this benchmark

What is LifeSci Diamond (2026-11)?

LifeSci Diamond is Arca's benchmark of 55 regulatory-affairs tasks (FDA/EMA submissions, labeling, compliance); practising specialists wrote or reviewed the answer keys for 44 of them. Scores are the strict pass rate: a task counts only when every rubric line is fully met and no penalty fires, as judged by GPT-6.1 Sol. One answer per task per model on the plain API with a web_search tool (Exa), provider default settings. 10 tasks are public; 45 are held out. Results are Arca's 4 November 2026 edition.

LifeSci Diamond (2026-11) is a text benchmark evaluating models on healthcare tasks. LLM Stats tracks 18 models on this benchmark, scored on a 0–1 scale. The current average is 0.0, with the leader at 0.2.

Compare leaders on the best AI for healthcare leaderboards.

Current leaders

GPT-6 Astra from OpenAI currently leads the LifeSci Diamond (2026-11) leaderboard with a score of 0.200 across 18 evaluated AI models.

1GPT-6 AstraOpenAI20.0%
2GPT-6.1 SolOpenAI14.5%
3Muse WonderMeta9.1%

FAQ

Common questions about the LifeSci Diamond (2026-11) benchmark and leaderboard.

What is the LifeSci Diamond (2026-11) benchmark?

LifeSci Diamond is Arca's benchmark of 55 regulatory-affairs tasks (FDA/EMA submissions, labeling, compliance); practising specialists wrote or reviewed the answer keys for 44 of them. Scores are the strict pass rate: a task counts only when every rubric line is fully met and no penalty fires, as judged by GPT-6.1 Sol. One answer per task per model on the plain API with a web_search tool (Exa), provider default settings. 10 tasks are public; 45 are held out. Results are Arca's 4 November 2026 edition.

What is the LifeSci Diamond (2026-11) leaderboard?

The LifeSci Diamond (2026-11) leaderboard ranks 18 AI models based on their performance on this benchmark. Currently, GPT-6 Astra by OpenAI leads with a score of 0.200. The average score across all models is 0.044.

What is the highest LifeSci Diamond (2026-11) score?

The highest LifeSci Diamond (2026-11) score is 0.200, achieved by GPT-6 Astra from OpenAI.

How many models are evaluated on LifeSci Diamond (2026-11)?

18 models have been evaluated on the LifeSci Diamond (2026-11) benchmark, with 0 verified results and 0 self-reported results.

Where can I find the LifeSci Diamond (2026-11) paper?

The LifeSci Diamond (2026-11) paper is available at https://www.arca.inc/blog/lifesci-diamond. The paper details the methodology, dataset construction, and evaluation criteria.

Where can I find the LifeSci Diamond (2026-11) dataset?

The LifeSci Diamond (2026-11) dataset is available at https://github.com/arcainc/lifesci-diamond.

What categories does LifeSci Diamond (2026-11) cover?

LifeSci Diamond (2026-11) is categorized under healthcare. The benchmark evaluates text models.

Which model offers the best value on LifeSci Diamond (2026-11)?

Among models scoring within 10% of the leader, GPT-6 Astra from OpenAI is the cheapest, at $10.00 per million input tokens with a score of 0.200.

How recent are the LifeSci Diamond (2026-11) leaderboard results?

The LifeSci Diamond (2026-11) leaderboard was last updated in November 2026 and currently includes 18 evaluated models.