Spaces:
Running
Running
Commit History
-
Update README.md
Verified signatured4b1022 -
Rename OpenMark.md to README.md
Verified signature7a0031b -
Update OpenMark.md
Verified signature4597772 -
Rename OpenMarkA.md to OpenMark.md
Verified signaturea9e38d4 -
Rename README.md to OpenMarkA.mdβ
Verified signature# OpenMark β AI Model Benchmarking Platform **Stop trusting leaderboards. Benchmark your own work.** [OpenMark](https://openmark.ai) lets you benchmark 100+ AI models on your own tasks with deterministic scoring, stability metrics, and real API cost tracking. ## What Makes OpenMark Different - **Your tasks, not generic tests** β Write any evaluation task (code review, classification, creative writing, vision analysis) and test models against it - **Deterministic scoring** β Same prompt, same score, every time. No vibes-based evaluation - **Stability metrics** β See which models change their answer across runs (hint: many do) - **Real API costs** β Know exactly what each model costs per task, not just per million tokens - **100+ models** β OpenAI, Anthropic, Google, Meta, Mistral, xAI, and more. Side-by-side comparison ## Why It Matters Generic benchmarks (MMLU, HumanEval, MATH) test models on tasks you'll never use. The only benchmark that matters is yours: does this model, with β¦ed5d3db -
initial commit
Verified signatureca7e191