BuilderBuilder
GPT-6.1 Sol · Rubik's cube, single turn
The episode says all four pass, Sol is cheapest, and the Claude runs take longer while staying under 15 minutes. All four unaided max ledgers judge-pass. Sol's API-equivalent is $0.25. Opus is 9m 41s and Sonnet is 11m 25s. HERO rendered capture Unaided model Open this round
Measured harness ledgerPublic result
GPT-6.1 Sol

Rubik's cube, single turn — GPT-6.1 Sol

Turn one face of a Rubik's cube a quarter turn by finger contact with two dexterous hands in MuJoCo.

Max reasoningHeadline result
Workflow cost
$0.25
Wall-clock
4m 29s
Processed tokens
773,009 processed (fresh input 58,092 + cache read 708,864 + cache creation 0 + output 6,053). Reasoning output 1,909 is a subset of output and is not added.
Record state
additive_harness_projection
Public summary

GPT-6.1 Sol Rubik's cube, single turn: 4m 29s, $0.25 API-equivalent estimate, 773,009 processed (fresh input 58,092 + cache read 708,864 + cache creation 0 + output 6,053). Reasoning output 1,909 is a subset of output and is not added..

Run identity and stack
  • Result ID: dex-cube-turn-mujoco-gpt-6.1-sol-max-codex-2026-10-02
  • Technical model: gpt-6.1-sol
  • Provider: OpenAI Codex
  • Client: Codex CLI 0.160.0
  • Stack: MuJoCo dexterous-hand fixture
  • Stack: Harness cube-turn prompt
Cost basis
  • Wall clock is supplied_measurements.wall_clock_display. Cost is supplied_measurements.cost.total API-equivalent. Charged amount is $0.
  • Source: supplied_measurements.token_usage.total_processed at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Validation evidence
  • Result: PASS
  • Verification: Task verdict is judge_pass_independently_replayed. The replay gate is that status. Additive projection from harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e. Broad harness sync was not run. Wall clock is supplied_measurements.wall_clock_display. Cost is supplied_measurements.cost.total API-equivalent. Charged amount is $0. Source: supplied_measurements.token_usage.total_processed at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Recorded caveats
  • Judge pass. Cycles-hero sha256 matches. This is the lowest API-equivalent of the four unaided max ledgers.
  • Wall clock is supplied_measurements.wall_clock_display. Cost is supplied_measurements.cost.total API-equivalent. Charged amount is $0.
  • Source: supplied_measurements.token_usage.total_processed at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Visible evidence gaps
  • additive projection; broad harness sync was not run
  • source harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e
Public result only

This result keeps its public summary and evidence, but it does not currently have a matching Builder test with prompts, projects, Harness workflows or skills.

Browse BuilderReturn to GPT-6.1 Sol
RemakeBenchResearch console