Claude Haiku 4.5, persona
OpinionsQA · Althing persona · default settings · 200 questions
synthpanel--claude-haiku-4-5--tdefault--tplcurrent--cb9ab3e1
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
30
± 0.7
SPS
SPS, 0 to 1
0.833
± 0.002
Distribution gap
mean JSD, lower is better
0.261
± 0.003
Rank agreement
Kendall τ, −1 to 1
0.572
± 0.004
Variance summary
- Replicates
- 3
- Std dev
- 0.7 Index points (SPS 0.002)
- Range
- Index 29 to 30 (SPS 0.831–0.835)
- Coefficient of variation (SPS)
- 0.0019
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 (3)
| Run | Timestamp | Index | SPS | JSD | Kendall τ | N |
|---|---|---|---|---|---|---|
| opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_170120 | 2026-04-11 17:01 UTC | 30 | 0.835 | 0.257 | 0.576 | 200 |
| opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_170451 | 2026-04-11 17:04 UTC | 29 | 0.831 | 0.263 | 0.572 | 200 |
| opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_170754 | 2026-04-11 17:07 UTC | 30 | 0.833 | 0.262 | 0.568 | 200 |