Skip to main content

Claude Haiku 4.5, raw

OpinionsQA · Raw LLM · default settings · 5 questions

raw--claude-haiku-4-5--tdefault--tplcurrent--055d7972

Compare with another OpinionsQA config → Claude Haiku 4.5 profile →

Metadata

Raw LLM · 7 replicates · 5 questions
Method
Raw LLM
Base provider
anthropic
Model
claude-haiku-4-5
Dataset
OpinionsQA
Temperature
default
Reasoning effort
default
Template
current
Samples / question
10
Questions
5
First replicate
2026-04-10 15:31 UTC
Last replicate
2026-04-10 21:04 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
20
± 18.2
SPS
SPS, 0 to 1
0.811
± 0.043
Distribution gap
mean JSD, lower is better
0.289
± 0.020
Rank agreement
Kendall τ, −1 to 1
0.534
± 0.025

Variance summary

Replicates
7
Std dev
18.2 Index points (SPS 0.043)
Range
Index -20 to 34 (SPS 0.715–0.842)
Coefficient of variation (SPS)
0.0531

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 (7)

Run Timestamp Index SPS JSD Kendall τ N
opinionsqa_raw-anthropic_claude-haiku-4-5-20251001_20260410_153134 2026-04-10 15:31 UTC -20 0.715 0.320 0.498 50
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_200754 2026-04-10 20:07 UTC 34 0.842 0.257 0.577 5
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_200814 2026-04-10 20:08 UTC 27 0.827 0.270 0.515 17
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_201800 2026-04-10 20:18 UTC 27 0.826 0.289 0.543 30
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_201830 2026-04-10 20:18 UTC 24 0.821 0.295 0.524 30
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_210418 2026-04-10 21:04 UTC 27 0.826 0.288 0.543 30
opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_210456 2026-04-10 21:04 UTC 24 0.820 0.302 0.536 30