JumalAIta IntelligenceIndependent evaluation

Benchmarks / Model

Kimi K3

Results for Kimi K3 by Moonshot AI across JumalAIta Intelligence benchmarks, with the configuration and run details of every evaluation.

01 / Result

Creative Reimplementation Benchmark

Kimi K3

Rank 5

Moonshot AI · Single shot · High reasoning

Benchmark version
v1.0
Generation
Single shot
Reasoning effort
High
Harness
Kimi Code CLI 2.1.1
Run date
2026-09-26
Run environment
Reference container (see the protocol)
Run time
67 min 16 s
Tool calls
116
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

Evaluators' notes

  1. Rank 5

    Kimi K3

    According to the original authors, Kimi K3 places narrowly above GPT-6 Sol, on the strength of its visuals.

02 / Summary

Benchmark results

Results for Kimi K3, one row per benchmark.
BenchmarkVersionRankEvaluationConfigurationStatusResult
Creative Reimplementation Benchmarkv1.05Expert-rankedSingle shot · HighFinalDetails of Kimi K3 in Creative Reimplementation Benchmark
Organization
Moonshot AI
Benchmarks
1