Model ledger

GPT-5.6 Sol

OpenAI Codex · Provider not separately recorded · 26 recorded runs · 19 benchmarks. Open a run for its public headline result. Paid research access opens the full available ledger and configuration. Builder adds exact prompts, released projects, the RemakeBench Harness and production skills for the tests in its library.

Max reasoningUltra reasoningxhigh reasoning
Benchmark

Campfire under the stars

2 runs · Ultra, xhigh reasoning

Benchmark

CARVE

1 run · Max reasoning

Benchmark

ECHO Main Menu

1 run · Max reasoning

Benchmark

Explorable space-flight game

1 run · Ultra reasoning

Benchmark

F-117 Stealth Jet

1 run · Max reasoning

Benchmark

Fighter Game v1

1 run · Max reasoning

Benchmark

High-voxel-density Jungle Temple diorama

2 runs · Ultra, xhigh reasoning

Benchmark

High-voxel-density Oasis Outpost diorama

2 runs · Ultra, xhigh reasoning

Benchmark

High-voxel-density Shrine Village diorama

2 runs · Ultra, xhigh reasoning

Benchmark

Infinite cathedral corridor shader

2 runs · Ultra, xhigh reasoning

Benchmark

Interactive Three.js voxel map viewer

2 runs · Ultra, xhigh reasoning

Benchmark

JRPG boss battle

1 run · Ultra reasoning

Benchmark

MacBook-class cinematic ad scene

1 run · xhigh reasoning

Benchmark

Neo-gothic storm city shader

2 runs · Ultra, xhigh reasoning

Benchmark

Off-road Mud Game

1 run · Max reasoning

Benchmark

Red Sands v1

1 run · Max reasoning

Benchmark

Sekiro Main Menu

1 run · Max reasoning

Benchmark

Space Flight Stage 2 — Landfall

1 run · Ultra reasoning

Benchmark

The Last of Us Main Menu

1 run · Max reasoning

RemakeBenchResearch console