Claude Haiku 4.5, persona (temperature 0.5)

Name: SynthBench Leaderboard
Creator: SynthBench
License: https://opensource.org/licenses/MIT

OpinionsQA · US adults

Index on OpinionsQA 35 above random answers (0); real people score 100

opinionsqa_synthpanel_openrouter_anthropic_claude-haiku-4-5 t=0.5_20260411_142602

Configuration

Althing persona · temperature 0.5 · default template

Method: Althing persona
Base provider: anthropic
Model: claude-haiku-4-5
Dataset: OpinionsQA
Temperature: 0.5
Reasoning effort: default
Template: current
Samples/question: 30
Timestamp: 2026-04-11T14:26:02Z

View all replicates for this config → Claude Haiku 4.5 profile →

Aggregate scores

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 run's dataset. The leaderboard averages it over the core datasets.

Loading scores…

Per-question detail All OpinionsQA questions, ranked by divergence →

Modal answer differs from human Topic

Per-question results for this run. Select a column header to sort; expand a row via the button in the Question column for full distribution bars.

Loading per-question detail…