Gemini 2.5 Flash-Lite, persona (temperature 1.2)
OpinionsQA · Althing persona · temperature 1.2 · default template · 100 questions
synthpanel--gemini-2.5-flash-lite--t1.2--tplcurrent--8e8049ef
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
39
± 0.5
SPS
SPS, 0 to 1
0.856
± 0.001
Distribution gap
mean JSD, lower is better
0.232
± 0.004
Rank agreement
Kendall τ, −1 to 1
0.610
± 0.000
Variance summary
- Replicates
- 2
- Std dev
- 0.5 Index points (SPS 0.001)
- Range
- Index 39 to 40 (SPS 0.855–0.857)
- Coefficient of variation (SPS)
- 0.0015
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=1.2_20260411_164350 | 2026-04-11 16:43 UTC | 40 | 0.857 | 0.229 | 0.610 | 100 |
| opinionsqa_synthpanel_openrouter_google_gemini-2.5-flash-lite t=1.2_20260411_164544 | 2026-04-11 16:45 UTC | 39 | 0.855 | 0.235 | 0.610 | 100 |