Show HN: OmnisBench, a re-gradable, open LLM routing benchmark on fresh tasks
OmnisBench Open, reproducible benchmark for LLM routing efficiency — how close a routing policy gets to the ideal quality-per-dollar frontier. Prior art: RouterBench (Martian, arXiv:2403.12031). OmnisBench differs by being live, cost-current, and continuously re-gradable (omnisbench verify). ⚠️ Security warning: untrusted code execution omnisbench run executes untrusted, model-generated Python in order to grade code tasks (the code_unittest grader).
- ▪OmnisBench Open, reproducible benchmark for LLM routing efficiency — how close a routing policy gets to the ideal quality-per-dollar frontier.
- ▪Prior art: RouterBench (Martian, arXiv:2403.12031).
- ▪OmnisBench differs by being live, cost-current, and continuously re-gradable (omnisbench verify). ⚠️ Security warning: untrusted code execution omnisbench run executes untrusted, model-generated Python in order to grade code tasks (the code
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,190 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/Fortitude-Group/OmnisBench |
| Publication time | Wed, 16 Sep 2026 14:25:52 +0000 |
| Retrieval time | 2026-09-16T14:38:41.582Z |
| Last seen | 2026-09-16T14:38:41.582Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | W_lTetOHR_Ch · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
OmnisBench Open, reproducible benchmark for LLM routing efficiency — how close a routing policy gets to the ideal quality-per-dollar frontier. Apache-2.0. Prior art: RouterBench (Martian, arXiv:2403.12031). OmnisBench differs by being live, cost-current, and continuously re-gradable (omnisbench verify). ⚠️ Security warning: untrusted code execution omnisbench run executes untrusted, model-generated Python in order to grade code tasks (the code_unittest grader). The v0 sandbox (src/omnisbench/graders/sandbox.py) provides a fresh subprocess, a hard timeout, and a throwaway working directory — but it does NOT provide network isolation, filesystem isolation, or memory/ resource limits.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.