List your company

Task Performance on Warehouse

12Turns TakenGPT-5.2 Instant
11.411.71212.3May 29, 2026

Evaluation results

MethodLinks
GPT-5.2 Instant2026.0512—
Claude Opus 4.72026.0512—
Claude Sonnet 4.62026.0512—
Gemini 3.1 Pro Preview2026.0512—
Qwen3 235B2026.0512—