vision-bench
Skillby glebis
Score and compare images using vision LLMs as judges. YAML-defined criteria presets for 11 use cases (text-to-image, photorealism, document OCR, charts, UI, portrait, product, scientific, invoice, alt-text, artistic style). Supports OpenAI, Anthropic, Gemini, Mistral, and OpenRouter as judge providers. Keys auto-decrypted via SOPS + age.
Details
- Path
- vision-bench
- Bundled scripts
- 4
- Dependencies
- 1
Bundled scripts
- vision-bench/bench.py
- vision-bench/vault.py
- vision-bench/judge.py
- vision-bench/report.py