Skip to main content

Claude Haiku 4.5, persona

OpinionsQA · Althing persona · default settings · 80 questions

synthpanel--claude-haiku-4-5--tdefault--tplcurrent--0b043f6f

Compare with another OpinionsQA config → Claude Haiku 4.5 profile →

Metadata

Althing persona · 3 replicates · 80 questions
Method
Althing persona
Base provider
anthropic
Model
claude-haiku-4-5
Dataset
OpinionsQA
Temperature
default
Reasoning effort
default
Template
current
Samples / question
50
Questions
80
First replicate
2026-04-11 15:54 UTC
Last replicate
2026-04-11 16:02 UTC

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
33
± 0.9
SPS
SPS, 0 to 1
0.842
± 0.002
Distribution gap
mean JSD, lower is better
0.239
± 0.007
Rank agreement
Kendall τ, −1 to 1
0.617
± 0.003

Variance summary

Replicates
3
Std dev
0.9 Index points (SPS 0.002)
Range
Index 33 to 34 (SPS 0.841–0.844)
Coefficient of variation (SPS)
0.0025

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_155441 2026-04-11 15:54 UTC 33 0.841 0.242 0.620 80
opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_155741 2026-04-11 15:57 UTC 33 0.841 0.244 0.614 80
opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5_20260411_160235 2026-04-11 16:02 UTC 34 0.844 0.231 0.617 80