Show HN: FrontierHarness Eval – 9 harness, same model, cost per pass varies 17x

# FrontierHarness Eval Source: [https://frontierharness.org/](https://frontierharness.org/) ### Pass rate ### Median cost per successful task ### Median cost per task ### Median cache hit rate per successful task ### Median time per successful task ## Beyond the numbers 1. 01**OpenCode: failures excluded\.** It only covers15passes\. Count failed attempts and the number becomes $3\.24per task\. 2. 02**Cache hit rate is not cost\.** A cached 300\-turn failure can still burn more than a short cache miss\. 3. 03**Quality and cost can diverge\.** Claude Codepasses19tasks, but reaches $18\.34in cost per task\. ## Run your harness on Runta\. If you want to test your own harness on Runta, we’ll give you $100 in credits to get started\. [Get $100 in credits](https://dashboard.runta.com/request-demo)[Start free trial](https://dashboard.runta.com/) ## Tested harnesses **Codex** `v0\.148\.0` **DeepSeek Harness** `v0\.1\.0\-rc\.8` **Claude Code** `v2\.1\.237` **Pi** `v0\.84\.2` **Oh My Pi** `v17\.4\.0` **Kimi Code** `v0\.37\.2` **Exo Harness** `v0\.1\.0` **OpenCode** `v1\.18\.19` **Hermes** `v0\.20\.4` - FrontierHarness v1\.0 focuses on software engineering contexts and terminal\-based tasks\. It may not generalize to other areas of knowledge work\. - Evaluated on Runta agent runtimes\. All harnesses and the task environment are prepared once as a golden checkpoint\. Every run is a fresh restore with identical vCPU, memory, disk size, disk contents, and memory state\.