Skip to main content

Majority answer

OpinionsQA · Baseline · default settings · 80 questions

baseline--majority-baseline--tdefault--tplcurrent--0bda5915

Compare with another OpinionsQA config →

Metadata

Baseline · 4 replicates · 80 questions
Method
Baseline
Base provider
—
Model
majority-baseline
Dataset
OpinionsQA
Temperature
default
Reasoning effort
default
Template
current
Samples / question
5
Questions
80
First replicate
2026-04-10 20:23 UTC
Last replicate
2026-04-10 20:59 UTC

Aggregated metrics

Mean across replicates, ± sample standard deviation (shown only with 2+ replicates). SynthBench Index: 0 = random answers, 100 = real people. SPS is the raw 0 to 1 score it is computed from. Index = 100 × (SPS − SPS of random answers) ÷ (human ceiling − SPS of random answers), on this config's dataset. The leaderboard averages it over the core datasets.

Index
0 = random answers, 100 = real people
-29
± 8.8
SPS
SPS, 0 to 1
0.695
± 0.021
Distribution gap
mean JSD, lower is better
0.509
± 0.030
Rank agreement
Kendall τ, −1 to 1
0.207
± 0.069

Variance summary

Replicates
4
Std dev
8.8 Index points (SPS 0.021)
Range
Index -39 to -20 (SPS 0.670–0.714)
Coefficient of variation (SPS)
0.0300

Per-topic breakdown

Index per topic (mean across replicates; 0 = random answers, 100 = real people). All seven topics are shown; topics this config's questions don't cover are marked "no questions".

Show data table

Loading data…

Replicates (4)

Run Timestamp Index SPS JSD Kendall τ N
opinionsqa_majority-baseline_20260410_202342 2026-04-10 20:23 UTC -39 0.670 0.550 0.128 100
opinionsqa_majority-baseline_20260410_205931 2026-04-10 20:59 UTC -32 0.687 0.514 0.175 175
opinionsqa_majority-baseline_20260410_205940 2026-04-10 20:59 UTC -20 0.714 0.488 0.281 80
opinionsqa_majority-baseline_20260410_205953 2026-04-10 20:59 UTC -22 0.710 0.484 0.246 429