Stepfun Step 5 Preview lands on Artificial Analysis' Pareto frontier
AnodicElegy · hn · 2026-09-19
Artificial Analysis has added Stepfun's Step 5 Preview LLM, placing it on the Pareto frontier — meaning it leads on capability at its price point. Scores and benchmarks are available on the Artificial Analysis model page, marking another strong third-party showing for a Chinese lab.
More from Models
- Small models cut entity resolution costs 99% with 7x throughput, matching Fable within 1 point — hrishioa · 2026-09-20
- Researcher flags severe LLM degradation spreading across sessions on the same machine — doodlestein · 2026-09-20
- Four LLMs Play Doom: Jev Averages 5.63 Kills, 4.5x a Finetuned Qwen3.5-4B — shniydder · 2026-09-20
- Researcher flags severe LLM degradation as a mission-critical concern — doodlestein · 2026-09-20
- Jev as LLM-as-a-judge: 20-200x faster scoring for under $0.10 — minchoi · 2026-09-20
- Step 5 Preview Now Open to Try, Step Plan Subscription Free for Now — StepFun_ai · 2026-09-20