Skip to content

Benchmark

NoCha pair accuracy (retrieval-common)

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

42.1%
Mean
46.5%
Median
9.5%
Std dev
28.9%
10th percentile
51%
90th percentile
28.9%
Min
28.9%51%
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
BM25+GPT-4o (k=25)table: 3, view: retrieval-common, system: BM25, GPT-4o (k=25)· NoCha (arXiv:2406.16264v3) data46.5%
BM25+GPT-4o (k=5)table: 3, view: retrieval-common, system: BM25, GPT-4o (k=5)· NoCha (arXiv:2406.16264v3) data28.9%
BM25+GPT-4o (k=50)table: 3, view: retrieval-common, system: BM25, GPT-4o (k=50)· NoCha (arXiv:2406.16264v3) data51%

Data credits: Marzena Karpinska, Katherine Thai, Kyle Lo, Tanya Goyal and Mohit Iyyer. One Thousand and One Pairs, arXiv:2406.16264v3. CC BY 4.0 article numeric/protocol extract; restructured, printed values unchanged. No task, book or dataset rights asserted. (licence)