LOCA-Bench 256K
We show this table for reference; we do not rank on it.
Tests long-context agents as tool environments grow to a 256K-token environment description.
Benchmark score on LOCA-Bench 256K — October 29, 2026
We compile the LOCA-Bench 256K rows from provider self-reports. MiniMax M3.1 Flash leads the table at 60.3. We do not use these results to rank models overall.
1 modelAgenticCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (1 model)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | MiniMax M3.1 FlashMiniMax | 60.3 | Not reported | Closed |
How to read this leaderboard
Operator receipt: 1 sourced row is currently displayable on this page; the leading published row is MiniMax M3.1 Flash at 60.3.
Honest limit: The environment size does not identify the full model context limit. Scores from different environment sizes or agent scaffolds are not interchangeable.
About LOCA-Bench 256K
Year
2026
Format
Agent tasks with controlled tool-environment growth
The 256K lane stays separate from other environment sizes and agent scaffolds. MiniMax reports M3.1 Flash at 60.3 using the official implementation. The provider does not disclose a code revision, agent strategy, reasoning effort, seeds, or run count. This provider-run result is display-only and excluded from weighted ranking.
Freshness and provenance
Version
LOCA-Bench 256K 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does LOCA-Bench 256K measure?
Tests long-context agents as tool environments grow to a 256K-token environment description.
Which model scores highest on LOCA-Bench 256K?
MiniMax M3.1 Flash by MiniMax currently leads with a score of 60.3 on LOCA-Bench 256K.
How many models are evaluated on LOCA-Bench 256K?
1 AI models have published results on LOCA-Bench 256K in the BenchLM catalog.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.