# Terminal-Bench Hard leaderboard

Coding 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/coding-terminal-bench-hard

Every model the catalog carries a published Terminal-Bench Hard value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Task success rate |
| Tasks | Agentic coding and terminal tasks |
| Difficulty | Professional software engineering |
| Published by | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |

A display-only Artificial Analysis coding metric for agentic coding and terminal use on a harder Terminal-Bench slice.

## Terminal-Bench Hard ranking

No model in the catalog has a published Terminal-Bench Hard score. The benchmark is defined by Artificial Analysis model benchmarks, 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.
