Skip to content

Benchmark

BABILong qa5 1M

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

Models and systems measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

77.5%
Mean
76%
Median
12.5%
Std dev
63%
10th percentile
93.4%
90th percentile
63%
Min
63%93.4%
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
~ ARMT (137M) fine-tuneqa5, 1M· BABILong v0 data docs93.4%
~ RMT (137M) fine-tuneqa5, 1M· BABILong v0 data docs63%
Llama3-ChatQA-1.5-8B + RAGqa5, 1M· BABILong v0 data docs76%

Data credits: RMT-team, Kuratov et al. Official v0 numeric CSV; results licence not separately stated.