Skip to main content

GPT-4o mini, persona (temperature 0.85)

OpinionsQA · Althing persona · temperature 0.85 · default template · 100 questions

synthpanel--gpt-4o-mini--t0.85--tplcurrent--d8521099

Metadata

Althing persona · 2 replicates · 100 questions
Method
Althing persona
Base provider
openai
Model
gpt-4o-mini
Dataset
OpinionsQA
Temperature
0.85
Reasoning effort
default
Template
current
Samples / question
30
Questions
100
First replicate
2026-04-11 15:22 UTC
Last replicate
2026-04-11 15:34 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
26
± 0.7
SPS
SPS, 0 to 1
0.824
± 0.002
Distribution gap
mean JSD, lower is better
0.287
± 0.003
Rank agreement
Kendall τ, −1 to 1
0.528
± 0.004

Variance summary

Replicates
2
Std dev
0.7 Index points (SPS 0.002)
Range
Index 25 to 26 (SPS 0.823–0.825)
Coefficient of variation (SPS)
0.0020

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 (2)

Run Timestamp Index SPS JSD Kendall τ N
opinionsqa_synthpanel_openrouter_openai_gpt-4o-mini t=0.85_20260411_152236 2026-04-11 15:22 UTC 25 0.823 0.289 0.525 100
opinionsqa_synthpanel_openrouter_openai_gpt-4o-mini t=0.85_20260411_153427 2026-04-11 15:34 UTC 26 0.825 0.285 0.530 100