# ExplorationBench AlienCode leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-exploration-bench-alien-code

ExplorationBench AlienCode Best@3. Every model the catalog carries a published ExplorationBench AlienCode value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Held-out accuracy (Best@3) |
| Tasks | 70 held-out program-synthesis tasks; 31 discovery targets |
| Difficulty | Discovering and applying unfamiliar executable rules |
| Published by | [ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds](https://arxiv.org/abs/2609.30199v1) |

Tests whether a system can discover a programming language's hidden rules through experiments and apply them to unseen tasks.

## ExplorationBench AlienCode ranking

No model in the catalog has a published ExplorationBench AlienCode score. The benchmark is defined by ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.