Benchmark
LOCA-Bench (256k)
What is LOCA-Bench (256k)?
LOCA-Bench is a long-context agentic benchmark. The 256k variant evaluates agents using the official ReAct mode with an environment description length of 256k…
- Modality
- text
- Evaluates
- reasoning, agents
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
LOCA-Bench (256k) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MiniMax M3 | MiniMax | 0.493 | 2026-06-01 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.