Skip to content

Benchmark

GDM-MRCRv2: 8 needle 8k

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

Models measured
68
Scores recorded
177
Sources
1
IQ weight
2.96

Score distribution

79.6%
Mean
89.2%
Median
21.3%
Std dev
47.2%
10th percentile
99.3%
90th percentile
19.8%
Min
19.8%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.96 for chat models, measured over 68 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 151–177 of 177 results.