Axion 1.0 - FrontierScience Research Rubric: leaderboard
Axion 1.0 author-run ReAct environment with web search, webpage visits, scholarly retrieval and Python. Best single run of three, or five for BioMysteryBench human-difficult; benchmark-approved website restrictions apply. Full HLE restricted websites and HLE-130 text-only are separate populations. Externally reported baseline scores are not pooled. FrontierScience Research Rubric. Native average rubric score, distinct from Research accuracy; source does not establish a theoretical rubric maximum.
Metric: Average rubric score. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Axion 1.0-122B (Axion Run: harness=ReAct; selection=best%20of%203) | 7.09 | |
| 2 | Axion 1.0-35B (Axion Run: harness=ReAct; selection=best%20of%203) | 6.67 |
Interactive version: theaggregate.ai/benchmark?slug=axion-1-0-frontierscience-research-rubric · How It Works · Data refreshed daily, snapshot 2026-11-05.