Skip to content

Benchmark

FictionLiveBench 16k

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

Models measured
54
Scores recorded
57
Sources
1
IQ weight
1.89

Score distribution

62%
Mean
62.5%
Median
18.3%
Std dev
40.6%
10th percentile
86.1%
90th percentile
25%
Min
25%97.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.89 for chat models, measured over 54 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–57 of 57 results.

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