Skip to content

Benchmark

GDM-MRCRv2: 8 needle 256k

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

Models measured
45
Scores recorded
128
Sources
1
IQ weight
1.85

Score distribution

39.4%
Mean
39.8%
Median
21%
Std dev
10.4%
10th percentile
69.1%
90th percentile
1.2%
Min
1.2%89%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.85 for chat models, measured over 45 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 101–128 of 128 results.