Benchmarks / Creative Reimplementation / Result
GPT-6 Sol
Rank 6Final
GPT-6 Sol by OpenAI in the Creative Reimplementation Benchmark. Rank 6 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
- Codex 0.157.0
- Run date
- 2026-09-25
- Run environment
- Reference container (see the protocol)
- Run time
- 23 min 07 s
- Tool calls
- 50
- 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
- 2026-09-25
