Gemini 2.5 Flash-Lite, persona (temperature 1.8)
OpinionsQA · Althing persona · temperature 1.8 · default template · 100 questions
synthpanel--gemini-2.5-flash-lite--t1.8--tplcurrent--4c7f113a
Failed to load configuration data.
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
40
± 2.2
SPS
SPS, 0 to 1
0.857
± 0.005
Distribution gap
mean JSD, lower is better
0.230
± 0.014
Rank agreement
Kendall τ, −1 to 1
0.613
± 0.003
Variance summary
- Replicates
- 2
- Std dev
- 2.2 Index points (SPS 0.005)
- Range
- Index 38 to 41 (SPS 0.853–0.861)
- Coefficient of variation (SPS)
- 0.0062
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_google_gemini-2.5-flash-lite t=1.8_20260411_164931 | 2026-04-11 16:49 UTC | 41 | 0.861 | 0.220 | 0.615 | 100 |
| opinionsqa_synthpanel_openrouter_google_gemini-2.5-flash-lite t=1.8_20260411_165130 | 2026-04-11 16:51 UTC | 38 | 0.853 | 0.240 | 0.611 | 100 |