BuilderBuilder
GPT-6.1 Sol · Rubik's cube, three turns
The episode says all four pass, Sol takes 2 hours 31 minutes and is still the cheapest, Sonnet is the most expensive, and Astra costs more than Opus. Sol's display is 151m 49s and the API-equivalent is $3.49. Sonnet is $18.19. Astra is $15.97 and Opus is $4.75. All four judge-pass. HERO rendered capture Unaided model Open this round
Measured harness ledgerPublic result
GPT-6.1 Sol

Rubik's cube, three turns — GPT-6.1 Sol

Complete the three-move Rubik's cube sequence D, F', U2 with regrasp, using two dexterous hands in MuJoCo.

Max reasoningHeadline result
Workflow cost
$3.49
Wall-clock
151m 49s
Processed tokens
11,502,325 processed (fresh input 418,751 + cache read 10,927,872 + cache creation 0 + output 155,702). Reasoning output 118,907 is a subset of output and is not added.
Record state
additive_harness_projection
Public summary

GPT-6.1 Sol Rubik's cube, three turns: 151m 49s, $3.49 API-equivalent estimate, 11,502,325 processed (fresh input 418,751 + cache read 10,927,872 + cache creation 0 + output 155,702). Reasoning output 118,907 is a subset of output and is not added..

Run identity and stack
  • Result ID: dex-cube-turn-mujoco-stage-2-three-moves-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 stage-2 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. 151m 49s matches the spoken 2 hours 31 minutes. This is GPT-6.1 Sol, not GPT-6 Sol. Cycles-hero sha256 matches.
  • 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