Skip to main content

Claude Haiku 4.5, raw

OpinionsQA · Raw LLM · default settings · 30 questions

raw--claude-haiku-4-5--tdefault--tplcurrent--d6080248

Compare with another OpinionsQA config → Claude Haiku 4.5 profile →

Metadata

Raw LLM · 4 replicates · 30 questions
Method
Raw LLM
Base provider
anthropic
Model
claude-haiku-4-5
Dataset
OpinionsQA
Temperature
default
Reasoning effort
default
Template
current
Samples / question
5
Questions
30
First replicate
2026-04-10 20:16 UTC
Last replicate
2026-04-10 21:03 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
27
± 1.3
SPS
SPS, 0 to 1
0.828
± 0.003
Distribution gap
mean JSD, lower is better
0.285
± 0.007
Rank agreement
Kendall τ, −1 to 1
0.546
± 0.005

Variance summary

Replicates
4
Std dev
1.3 Index points (SPS 0.003)
Range
Index 26 to 29 (SPS 0.824–0.831)
Coefficient of variation (SPS)
0.0038

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
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_201657 2026-04-10 20:16 UTC 28 0.829 0.279 0.545 30
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_201725 2026-04-10 20:17 UTC 26 0.824 0.293 0.541 30
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_210315 2026-04-10 21:03 UTC 27 0.826 0.289 0.546 30
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_210344 2026-04-10 21:03 UTC 29 0.831 0.278 0.553 30