Wow, Step 5 preview is looking really good on benchmarks.
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
Wow, Step 5 preview is looking really good on benchmarks. Artificial Analysis Intelligence Index (v4.3.2) is updated Step 5 preview has a score of 44 Beats - Gemini 3.8 flash (high) - 41 - Deepseek-v4.1-flash (max) - 39 - GLM 5.3-flash - 42 - GPT-5.6-Sol (high) - 42 Same score as Kimi K3 (max) - 44 One score less than Qwen3.8-0902-max and Grok-4.6-high (both at 45). It's beating many models significantly bigger in size. Best part is, it's going to be open and we will be getting it's weight on October 15th.
Posted by AJ (7.6k followers) 1 h ago · 1 likes · 242 views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Apple Foundation Advanced running on A20 Pro — @imnotchalk
- Kimi-k3.1，中秋之前会上线，我预估是中秋前一天。。。给大家来个大的，大家都别休息 — @mylifcc
- Step 5 preview is here. — @ItsmeAjayKV
- 🚨BREAKING: China's StepFun has officially launched Step 5 Preview, a 600B MoE model… — @choblin29
- new step 5 model with 68% on deepswe and 33% on tbench4.0 looks solid — @zainhas
- Step 5 Preview from @StepFun_ai is 600B params total where only 27B are active, and… — @plotarmordev
- DeepSeek 2.0 Leak: Coming Soon 🔥 — @Priyannkaaaa
- Introducing Da7em Bench. — @Da7_Tech
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 31.8k posts from 4.8k X accounts over the last 14 days, 1.4k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 06:30 UTC. Full method.