Model ledger

Qwen3.8 Max Preview

Alibaba Cloud Model Studio · 11 recorded runs · 10 benchmarks. Open a run for its public headline result. Paid research access opens the full available ledger and configuration. Builder also includes the separate, immutable Tech Review 001 prompt and data package for its 28 named runs.

Mandatory thinking enabled reasoningUnreported reasoning

← All models Enter a blind battle

Benchmark

Campfire Under a Starry Night

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported6m 0.9s wall-clockWall-clock

Benchmark

Interactive Voxel Map Viewer

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported45m 25.4s wall-clockWall-clock

Benchmark

JRPG Boss Battle

1 run · Mandatory thinking enabled reasoning

01Qwen3.8 Max Preview Mandatory thinking enabled58m 40.6s wall-clockWall-clock

Benchmark

Jungle Temple

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported48m 49.9s wall-clockWall-clock

Benchmark

MacBook-Class Cinematic

1 run · Mandatory thinking enabled reasoning

01Qwen3.8 Max Preview Mandatory thinking enabled7h 00m 56.4s wall-clockWall-clock

Benchmark

Neo-Gothic Storm City

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported7m 56.8s wall-clockWall-clock

Benchmark

Oasis Outpost

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported34m 48.5s wall-clockWall-clock

Benchmark

Shrine Village

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported30m 59.8s wall-clockWall-clock

Benchmark

Space Flight Game

2 runs · Unreported reasoning

01Qwen3.8 Max Preview Unreported2h 4m 17.3s wall-clockWall-clock 02Qwen3.8 Max Preview Unreported38m 43.2s wall-clockWall-clock

Benchmark

Stained Glass Cathedral Shader

1 run · Unreported reasoning

01Qwen3.8 Max Preview Unreported25m 9.2s wall-clockWall-clock