# Arena Agent leaderboard

external 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://modelchoice.dev/leaderboards/benchmarks/external-arena-agent

Every model the catalog carries a published Arena Agent value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Agent Capability Index (higher is better) |
| Tasks | Real Agent Mode sessions on arena.ai |
| Difficulty | Multi-step agent work chosen by users |
| Published by | [Arena Agent leaderboard](https://arena.ai/leaderboard/agent) |

Arena ranks models by how they do in real Agent Mode sessions on arena.ai. Since November 18, 2026 the board is the Agent Capability Index, one score built from four session signals: task outcome, praise vs complaint, steering burden and bash reliability.

## Arena Agent ranking

No model in the catalog has a published Arena Agent score. The benchmark is defined by Arena Agent leaderboard, 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.
