long context benchmark
NoLiMa 32K
NoLiMa evaluated at a 32768-token context length. Tests latent associative reasoning in long contexts with minimal lexical overlap between questions and needles.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
NoLiMa 32K Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 54.5% | 100.0% | 1 | C |
NoLiMa 32K Highlights
The leading models and scores on this benchmark.
What is NoLiMa 32K?
What NoLiMa 32K measures and how its scores work.
NoLiMa evaluated at a 32768-token context length. Tests latent associative reasoning in long contexts with minimal lexical overlap between questions and needles.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- NoLiMa 32K
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- nolima-32k|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about NoLiMa 32K.
Which model scores highest on NoLiMa 32K?
MiniCPM-SALA is currently ranked first with 54.5%.
What does NoLiMa 32K measure?
NoLiMa evaluated at a 32768-token context length. Tests latent associative reasoning in long contexts with minimal lexical overlap between questions and needles.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.