Skip to main content

Gemini 2.5 Flash-Lite, persona

SubPOP · Althing persona · default settings · 100 questions

synthpanel--gemini-2.5-flash-lite--tdefault--tplcurrent--9c3e70d1

Metadata

Althing persona · 2 replicates · 100 questions
Method
Althing persona
Base provider
google
Model
gemini-2.5-flash-lite
Dataset
SubPOP
Temperature
default
Reasoning effort
default
Template
current
Samples / question
15
Questions
100
First replicate
2026-04-11 23:42 UTC
Last replicate
2026-07-14 17:17 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
1
± 43.6
SPS
SPS, 0 to 1
0.761
± 0.104
Distribution gap
mean JSD, lower is better
0.274
± 0.009
Rank agreement
Kendall τ, −1 to 1
0.541
± 0.052

Variance summary

Replicates
2
Std dev
43.6 Index points (SPS 0.104)
Range
Index -29 to 32 (SPS 0.687–0.834)
Coefficient of variation (SPS)
0.1363

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
subpop_synthpanel_openrouter_google_gemini-2.5-flash-lite_20260411_234245 2026-04-11 23:42 UTC 32 0.834 0.267 0.578 100
subpop_synthpanel_openrouter_google_gemini-2.5-flash-lite_20260714_171729 2026-07-14 17:17 UTC -29 0.687 0.280 0.505 100