Skip to main content

Claude Haiku 4.5, persona (temperature 1)

OpinionsQA · Althing persona · temperature 1 · default template · 100 questions

synthpanel--claude-haiku-4-5--t1.0--tplcurrent--cb2ade28

Compare with another OpinionsQA config → Claude Haiku 4.5 profile →

Metadata

Althing persona · 3 replicates · 100 questions
Method
Althing persona
Base provider
anthropic
Model
claude-haiku-4-5
Dataset
OpinionsQA
Temperature
1
Reasoning effort
default
Template
current
Samples / question
30
Questions
100
First replicate
2026-04-11 14:15 UTC
Last replicate
2026-04-11 14:30 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
34
± 3.1
SPS
SPS, 0 to 1
0.844
± 0.007
Distribution gap
mean JSD, lower is better
0.237
± 0.012
Rank agreement
Kendall τ, −1 to 1
0.601
± 0.012

Variance summary

Replicates
3
Std dev
3.1 Index points (SPS 0.007)
Range
Index 31 to 37 (SPS 0.837–0.851)
Coefficient of variation (SPS)
0.0087

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 t=1.0_20260411_141532 2026-04-11 14:15 UTC 35 0.845 0.250 0.591 100
opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5 t=1.0_20260411_142642 2026-04-11 14:26 UTC 37 0.851 0.237 0.597 100
opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5 t=1.0_20260411_143053 2026-04-11 14:30 UTC 31 0.837 0.225 0.614 100