GPT-4o mini, persona (temperature 0.5)
OpinionsQA · Althing persona · temperature 0.5 · default template · 100 questions
synthpanel--gpt-4o-mini--t0.5--tplcurrent--4785bf4b
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
25
± 0.3
SPS
SPS, 0 to 1
0.822
± 0.001
Distribution gap
mean JSD, lower is better
0.293
± 0.002
Rank agreement
Kendall τ, −1 to 1
0.529
± 0.001
Variance summary
- Replicates
- 2
- Std dev
- 0.3 Index points (SPS 0.001)
- Range
- Index 25 to 25 (SPS 0.821–0.822)
- Coefficient of variation (SPS)
- 0.0009
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=0.5_20260411_151713 | 2026-04-11 15:17 UTC | 25 | 0.822 | 0.292 | 0.530 | 100 |
| opinionsqa_synthpanel_openrouter_openai_gpt-4o-mini t=0.5_20260411_152843 | 2026-04-11 15:28 UTC | 25 | 0.821 | 0.294 | 0.528 | 100 |