JumalAIta IntelligenceIndependent evaluation

Benchmarks / Model

Gemini 3.8 Flash

Results for Gemini 3.8 Flash by Google across JumalAIta Intelligence benchmarks, with the configuration and run details of every evaluation.

01 / Result

Creative Reimplementation Benchmark

Gemini 3.8 Flash

Disqualified

Google · Single shot · High reasoning

Rule violation
Disqualified: the model downloaded the original demo from scene.org and read its info files, which the benchmark rules forbid. The comparison recording carries a rule violation label.
Benchmark version
v1.0
Generation
Single shot
Reasoning effort
High
Harness
Antigravity CLI 1.2.11
Run date
2026-09-26
Run environment
Reference container (see the protocol)
Run time
18 min 29 s
Tool calls
105
Cost
Not yet published
Tokens
Not yet published
Evaluators
The original authors of the reference demo (members of Jumalauta)
Recording length
2 min 55 s
Recording published
2026-09-26

02 / Summary

Benchmark results

Results for Gemini 3.8 Flash, one row per benchmark.
BenchmarkVersionRankEvaluationConfigurationStatusResult
Creative Reimplementation Benchmarkv1.0DQExpert-rankedSingle shot · HighFinalDetails of Gemini 3.8 Flash in Creative Reimplementation Benchmark
Organization
Google
Benchmarks
1