Skip to content

Benchmark

BABILong qa2 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

41%
Mean
22%
Median
41.8%
Std dev
2%
10th percentile
99%
90th percentile
2%
Min
2%99%
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-tuneqa2, 1M· BABILong v0 data docs99%
~ RMT (137M) fine-tuneqa2, 1M· BABILong v0 data docs22%
Llama3-ChatQA-1.5-8B + RAGqa2, 1M· BABILong v0 data docs2%

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