BuilderBuilder
GPT-6.1 Sol · Snowboarding
The episode says the runs are playable and under two hours, and that the Claude builds flicker at the end of the map. Every ledger here is a partial or asset-judge failure. Those states stay. The selected clocks are all under two hours, which agrees with the spoken duration without turning it into a pass. Supplied source capture Unaided model Open this round
Measured harness ledgerPublic result
GPT-6.1 Sol

Snowboarding — GPT-6.1 Sol

Build a playable Babylon.js WebGPU snowboarding game with the supplied rider asset, carved terrain, tricks, obstacles, audio, and a complete downhill run.

Max reasoningHeadline result
Workflow cost
$19.89
Wall-clock
1h 59m 59s
Processed tokens
Fresh input 2,577,012, cached input 93,784,576, output 535,789. These components are not summed into a processed total.
Record state
additive_harness_projection
Public summary

GPT-6.1 Sol Snowboarding: 1h 59m 59s, $19.89 API-equivalent estimate, Fresh input 2,577,012, cached input 93,784,576, output 535,789. These components are not summed into a processed total..

Run identity and stack
  • Result ID: carve-webgpu-snowboarding-gpt-6.1-sol-max
  • Technical model: gpt-6.1-sol
  • Provider: OpenAI Codex
  • Client: Codex CLI
  • Stack: Babylon.js WebGPU
  • Stack: Supplied snowboarder fixture
  • Stack: Harness v1 CARVE prompt
Cost basis
  • Clock is the root generation start to stopped_at_utc under a 7200-second hard limit. Cost is cost.estimated_usd, token-only API-equivalent. External tool charges are unknown and excluded.
  • Source: cost.fresh_input_tokens, cost.cached_input_tokens, cost.output_tokens at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Validation evidence
  • Result: partial_gameplay_pass_asset_batch_fail
  • Verification: Recorded status is partial_gameplay_pass_asset_batch_fail. Pending, partial, stopped, qualified, and model-finished states stay unjudged. Additive projection from harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e. Broad harness sync was not run. Clock is the root generation start to stopped_at_utc under a 7200-second hard limit. Cost is cost.estimated_usd, token-only API-equivalent. External tool charges are unknown and excluded. Source: cost.fresh_input_tokens, cost.cached_input_tokens, cost.output_tokens at harness commit 9b7c614dbb5103cc373fdf6275b5c4efc10d8f0e.
Recorded caveats
  • Partial: gameplay pass and asset-batch fail. The run stopped on the two-hour cap. Not recorded as a full pass.
  • Clock is the root generation start to stopped_at_utc under a 7200-second hard limit. Cost is cost.estimated_usd, token-only API-equivalent. External tool charges are unknown and excluded.
  • Source: cost.fresh_input_tokens, cost.cached_input_tokens, cost.output_tokens 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