Artificial Analysis launches Optima: custom benchmarks, 10x cost reduction possible
ArtificialAnlys · x · 2026-08-14
Artificial Analysis launches Optima, a platform that lets anyone create custom benchmarks for their use case, leveraging their research and platform. Optima helps find the best model for a task or an equally performant alternative at 10x lower cost/time. The workflow integrates their benchmark research experience. DiligenceStack agent evals have been moved to Optima, with the author praising it as far better than previous methods.
Related event: Artificial Analysis Launches Optima for Custom LLM Benchmarks(4 posts)→
More from coding & agent
- Claude Code and Codex now autocomplete the user's next action — tokenbender · 2026-10-16
- Hermes Agent ships official Reverse Engineer Anything plugin with one-command setup — Teknium · 2026-10-16
- MLExpert: 35B MoE Agent Trained to Autonomously Handle Machine Learning Engineering — Shangheng Du · 2026-10-16
- Cowork-Gym: Alibaba Synthesizes 64.9K Agent Work Environments, Boosting Qwen by 8.7 Points — Anni Zou · 2026-10-16
- MMSearch-OPD: Joint RL and On-Policy Distillation for Long-Horizon Multimodal Search Agents — PekingUniversity · 2026-10-16
- A gallery of 214 projects built on one model shows the 'post your build' ad flywheel — gaganghotra_ · 2026-10-16