Skip to content

Benchmark

FictionLiveBench 192k

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

Models measured
18
Scores recorded
18
Sources
1
IQ weight
1.22

Score distribution

62.1%
Mean
65.6%
Median
18.8%
Std dev
37.5%
10th percentile
87.5%
90th percentile
28.6%
Min
28.6%90.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.22 for chat models, measured over 18 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)