Benchmark Heaven opens model submission queue with free and 48h fast-lane options
airesearch12 · x · 2026-10-05
Third-party benchmark site Benchmark Heaven (run by airesearch12) says evaluation requests are pouring in and will now only be accepted via its web form — no DMs, email, or GitHub issues. Submission is free, with a 48-hour fast lane option.
The site's ranking is customizable:
- Slider-based weighting of Intelligence, Calibration, Speed & Cost
- User-defined cost and latency caps defining "Jev-class" models
- Head-to-head radar chart comparison of any two models
- Filters by hosting region (China/EU/US), data confidentiality, open weights, and more
Benchmarks span coding agents, full-stack design Elo, Epoch ECI and more.
More from Models
- AI eval researcher: even humans can't detect subtle AI patterns like distributional biases — alexisjross · 2026-10-06
- At $20/month, OpenAI gives you everything, Google quietly tiers models by surface — bytebot · 2026-10-06
- ChatGPT puts real cartoonists' signatures on fake New Yorker cartoons — luisdans · 2026-10-06
- Dev bets Thinking Machines' "fledge alpha" will ship as "fledgling" — willcb · 2026-10-06
- Insider speculation: GPT-6.5 expected within 4 weeks, above Fable 5.5 level — VraserX · 2026-10-06
- Gemini users hit image generation limits as Google tightens daily quotas — BrattyMiku · 2026-10-06