Skip to main content

Gemini 2.5 Flash, raw

GlobalOpinionQA · Raw LLM · default settings · 100 questions

raw--gemini-2.5-flash--tdefault--tplcurrent--d5695573

Metadata

Raw LLM · 2 replicates · 100 questions
Method
Raw LLM
Base provider
google
Model
gemini-2.5-flash
Dataset
GlobalOpinionQA
Temperature
default
Reasoning effort
default
Template
current
Samples / question
15
Questions
100
First replicate
2026-04-11 23:41 UTC
Last replicate
2026-07-15 17:24 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
-6
± 6.5
SPS
SPS, 0 to 1
0.760
± 0.015
Distribution gap
mean JSD, lower is better
0.331
± 0.026
Rank agreement
Kendall τ, −1 to 1
0.265
± 0.034

Variance summary

Replicates
2
Std dev
6.5 Index points (SPS 0.015)
Range
Index -11 to -2 (SPS 0.750–0.770)
Coefficient of variation (SPS)
0.0192

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
globalopinionqa_openrouter_google_gemini-2.5-flash_20260411_234139 2026-04-11 23:41 UTC -2 0.770 0.313 0.289 100
globalopinionqa_openrouter_google_gemini-2.5-flash_20260715_172433 2026-07-15 17:24 UTC -11 0.750 0.349 0.241 100