Claude Haiku 4.5, persona
SubPOP · Althing persona · default settings · 200 questions
synthpanel--claude-haiku-4-5--tdefault--tplcurrent--fe74b735
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
19
± 4.4
SPS
SPS, 0 to 1
0.803
± 0.010
Distribution gap
mean JSD, lower is better
0.302
± 0.024
Rank agreement
Kendall τ, −1 to 1
0.496
± 0.033
Variance summary
- Replicates
- 4
- Std dev
- 4.4 Index points (SPS 0.010)
- Range
- Index 13 to 22 (SPS 0.787–0.809)
- Coefficient of variation (SPS)
- 0.0129
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 (4)
| Run | Timestamp | Index | SPS | JSD | Kendall τ | N |
|---|---|---|---|---|---|---|
| subpop_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_165150 | 2026-04-11 16:51 UTC | 22 | 0.809 | 0.288 | 0.514 | 200 |
| subpop_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_165448 | 2026-04-11 16:54 UTC | 22 | 0.809 | 0.287 | 0.514 | 200 |
| subpop_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_165736 | 2026-04-11 16:57 UTC | 20 | 0.804 | 0.298 | 0.510 | 200 |
| subpop_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260716_192337 | 2026-07-16 19:23 UTC | 13 | 0.787 | 0.337 | 0.447 | 200 |