Skip to content

Benchmark

NIAH-Multi

Long context benchmarks measure how well models use information in long inputs. Scores are percentages. Higher is better.

Models and systems measured
1
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

98.6%
Mean
99.3%
Median
1.2%
Std dev
96.7%
10th percentile
99.9%
90th percentile
96.7%
Min
96.7%99.9%
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
MiMo V2 Flash Baseofficial Base long-context table · 128K· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.98.6%
MiMo V2 Flash Baseofficial Base long-context table · 256K· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.7%
MiMo V2 Flash Baseofficial Base long-context table · 32K· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.3%
MiMo V2 Flash Baseofficial Base long-context table · 64K· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.9%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.