List your company

Preference Elicitation on SpecBench Task 1

74Improvement Rate (T0->T5)Buddy
49.0455.526268.48May 13, 2026

Evaluation results

MethodLinks
Buddy2026.05747792——0
Claude CodeBackbone=Opus-4.62026.05626780——1
Cursor CLIBackbone=GPT-5.4-mini2026.05626178——3
Gemini CLIBackbone=Gemini-2.5-pro2026.05505761——17