Skip to content

Benchmark

BABILong avg(qa1-5) 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

58.4%
Mean
42.8%
Median
24.8%
Std dev
39%
10th percentile
93.4%
90th percentile
39%
Min
39%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-tuneavg, 1M· BABILong v0 data docs93.4%
~ RMT (137M) fine-tuneavg, 1M· BABILong v0 data docs42.8%
Llama3-ChatQA-1.5-8B + RAGavg, 1M· BABILong v0 data docs39%

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