Benchmarks / Creative Reimplementation / Result
Grok 4.7
Rank 9Final
Grok 4.7 by xAI in the Creative Reimplementation Benchmark. Rank 9 of 13 in the order set by the original authors of the reference demo (members of Jumalauta).
01 / Result
Recording and run details
- Benchmark version
- v1.0
- Generation
- Single shot
- Reasoning effort
- High
- Harness
- Grok Build CLI 1.0.41
- Run date
- 2026-09-26
- Run environment
- Reference container (see the protocol)
- Run time
- 9 min 31 s
- Tool calls
- 138
- Cost
- Not yet published
- Tokens
- Not yet published
- Run note
- At 75.5 s the demo passes its credits to the room scene as an object and then calls credits.forEach, which throws on every frame and stops the render loop, so the picture freezes for the rest of the demo. A second run was started after this one to rule out a transient fault; the freeze comes from the model's own code, and only this first run is ranked.
- Evaluators
- The original authors of the reference demo (members of Jumalauta)
- Recording length
- 2 min 55 s
- Recording published
- 2026-09-26
Evaluators' notes
The original authors gave the following reasons for their order. They are reported here as the authors' views, not as findings of this site. No other evaluation comments have been published.
- Rank 9
Grok 4.7
According to the original authors, the code error in the demo and the resulting frozen visuals lower its placement.
