GPT-4o mini, raw
OpinionsQA · Raw LLM · default settings · 30 questions
raw--gpt-4o-mini--tdefault--tplcurrent--df386175
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
28
± 1.0
SPS
SPS, 0 to 1
0.830
± 0.002
Distribution gap
mean JSD, lower is better
0.280
± 0.005
Rank agreement
Kendall τ, −1 to 1
0.550
± 0.005
Variance summary
- Replicates
- 2
- Std dev
- 1.0 Index points (SPS 0.002)
- Range
- Index 28 to 29 (SPS 0.828–0.832)
- Coefficient of variation (SPS)
- 0.0028
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_openrouter_openai_gpt-4o-mini_20260410_210758 | 2026-04-10 21:07 UTC | 29 | 0.832 | 0.277 | 0.554 | 30 |
| opinionsqa_openrouter_openai_gpt-4o-mini_20260410_210925 | 2026-04-10 21:09 UTC | 28 | 0.828 | 0.283 | 0.547 | 30 |