CategoryAgentic
MeasureAgent tasks with controlled tool-environment growth
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.
Models ranked by their published LOCA-Bench 256K value| Rank | Model | Provider | Agent tasks with controlled tool-environment growth |
|---|
| 1 |  MiniMax M3.1 Flash | MiniMax | 60.3 |
Evidence key: Observed
Rows are ordered by the value LOCA-bench: Benchmarking Language Agents Under Controllable Environment Growth published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
About LOCA-Bench 256K
What the benchmark measures and how its value is published, from the source’s own record.
What is LOCA-Bench 256K?
LOCA-Bench 256K is an agentic benchmark published by LOCA-bench: Benchmarking Language Agents Under Controllable Environment Growth. Tests long-context agents as tool environments grow to a 256K-token environment description.
How is LOCA-Bench 256K scored?
Each model's result is published by LOCA-bench: Benchmarking Language Agents Under Controllable Environment Growth as agent tasks with controlled tool-environment growth. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 1 model that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale