# LOCA-Bench 256K 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-loca-bench256k

Every model the catalog carries a published LOCA-Bench 256K value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Agent tasks with controlled tool-environment growth |
| Tasks | — |
| Difficulty | — |
| Published by | [LOCA-bench: Benchmarking Language Agents Under Controllable Environment Growth](https://arxiv.org/abs/2602.07962) |

Tests long-context agents as tool environments grow to a 256K-token environment description.

## LOCA-Bench 256K ranking

1 model with a published LOCA-Bench 256K value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Agent tasks with controlled tool-environment growth | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [MiniMax M3.1 Flash](https://modelscale.dev/models/minimax-m3-1-flash) | MiniMax | 60.3 | Observed 2026-10-23 · source benchlm:models |

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.