Skip to main content

GPT-4o mini, raw

OpinionsQA · Raw LLM · default settings · 200 questions

raw--gpt-4o-mini--tdefault--tplcurrent--b057d2f1

Compare with another OpinionsQA config → GPT-4o mini profile →

Metadata

Raw LLM · 2 replicates · 200 questions
Method
Raw LLM
Base provider
openai
Model
gpt-4o-mini
Dataset
OpinionsQA
Temperature
default
Reasoning effort
default
Template
current
Samples / question
50
Questions
200
First replicate
2026-04-11 00:01 UTC
Last replicate
2026-04-11 00:16 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
19
± 0.0
SPS
SPS, 0 to 1
0.808
± 0.000
Distribution gap
mean JSD, lower is better
0.307
± 0.000
Rank agreement
Kendall τ, −1 to 1
0.478
± 0.000

Variance summary

Replicates
2
Std dev
0.0 Index points (SPS 0.000)
Range
Index 19 to 19 (SPS 0.808–0.808)
Coefficient of variation (SPS)
0.0000

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 (2)

Run Timestamp Index SPS JSD Kendall τ N
opinionsqa_openrouter_openai_gpt-4o-mini_20260411_000143 2026-04-11 00:01 UTC 19 0.808 0.307 0.478 200
opinionsqa_openrouter_openai_gpt-4o-mini_20260411_001612 2026-04-11 00:16 UTC 19 0.808 0.307 0.478 200