BuilderBuilder
Measured harness ledgerPublic result
GPT-6.1 Sol

Space flight — GPT-6.1 Sol

Build the browser space-flight game through stage-2 landfall. The episode comparison uses those four stage-2 captures. Narrated cost and duration match neither the stage-1 nor the stage-2 ledger fields.

Max reasoningHeadline result
Workflow cost
$3.71
Wall-clock
2h 28m 43s
Processed tokens
Total input 16,577,805 (fresh input 393,869 + cache read 16,183,936 + cache creation 0). Output generation 130,763 is not included in that input total. Reasoning subset 58,953 is inside output and is not added. No processed total is recorded.
Record state
additive_harness_projection
Public summary

GPT-6.1 Sol Space flight: 2h 28m 43s, $3.71 API-equivalent estimate, Total input 16,577,805 (fresh input 393,869 + cache read 16,183,936 + cache creation 0). Output generation 130,763 is not included in that input total. Reasoning subset 58,953 is inside output and is not added. No processed total is recorded..

Run identity and stack
  • Result ID: space-flight-game-threejs-gpt-6.1-sol-max-20261001
  • Technical model: gpt-6.1-sol
  • Provider: OpenAI Codex
  • Client: Codex CLI
  • Stack: Three.js space-flight workflow
  • Stack: Stage 1 and stage 2 landfall ledgers
Cost basis
  • Stage 1. Clock is measurements.model_invocation_wall_seconds. Cost is api_cost.total_usd. Actual subscription charge is null.
  • Source: measurements.token_usage.total_input at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Validation evidence
  • Result: QUALIFIED
  • Verification: Recorded status is session_finished_pending_acceptance. Pending, partial, stopped, qualified, and model-finished states stay unjudged. Additive projection from harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e. Broad harness sync was not run. Stage 1. Clock is measurements.model_invocation_wall_seconds. Cost is api_cost.total_usd. Actual subscription charge is null. Source: measurements.token_usage.total_input at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Recorded caveats
  • Stage 1. Verdict QUALIFIED while acceptance is pending. Not the stage-2 stopped run.
  • Stage 1. Clock is measurements.model_invocation_wall_seconds. Cost is api_cost.total_usd. Actual subscription charge is null.
  • Source: measurements.token_usage.total_input 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