Latest

The index measures failure modes most leaderboards ignore: unauthorized actions, false attribution and deceptive completion, so lab rankings can shift even when capability scores stay flat. Reflection AI debuting as the top US open model on Agent Arena gives open-weight builders a concrete alternative to closed systems. StepFun's entry at 75.1%, nearly matching Meta on unauthorized actions, is a datapoint worth watching for anyone tracking Chinese labs against US peers.

lmarena.ai@lmarena_ai11 sourcesSource

Usage on OpenRouter is a proxy for real developer demand, and 19.5T tokens in a first week puts Step 5 Preview alongside the most-routed open models worldwide. Teams choosing inference backends can compare its cost and throughput against Qwen and DeepSeek offerings on the same leaderboard. Its traction also signals continued Chinese lab momentum in the global API routing market.

官方账号阶跃星辰 Stepfun@Stepfun_AI6 sourcesSource

The claim of 24-hour agent endurance points at long-horizon automation rather than chat benchmarks, and the near-8K tokens/sec/GPU throughput figure shows quantised inference on GB300 is becoming a default release channel. Builders deploying open-weights agents can start from the SGLang or vLLM recipes. StepFun's open release also gives ASEAN teams an alternative to closed frontier APIs for self-hosted workloads.

官方账号NVIDIA AI@NVIDIAAI11 sourcesSource

A 1M-token context with self-checking behaviour makes this a practical pick for unattended long agent runs on unfamiliar codebases. Developers can plug it into existing tools like Cline or OpenCode without changing workflows, and the open-weights release on 15 Oct lets teams self-host. Its strong frontend generation and document-to-deck abilities also put it in direct comparison with frontier coding models for everyday engineering work.

elvis@omarsar05 sourcesSource

The non-obvious detail is the self-test-and-fix loop: rather than stopping after generating code, Step 5 Preview verified the game actually ran, which is what separates deliverable output from demo code. Builders choosing between Chinese flagship models for agentic coding work can use this hands-on comparison as a practical reference, since the three models faced the same unconstrained prompt and had to pick their own architecture and project structure.

掘金本周最热@猫猫头啊Source

Benchmark scores can hide whether a model survives long, multi-step builds, so the value here is watching Step 5 Preview handle mechanical synchronisation and real tooling rather than canned puzzles. Developers choosing between Step 5, GLM-5.3, Kimi K3 and Claude Opus 5 get a practical cost-versus-reliability comparison for agentic coding workflows. The stated price gap makes it a concrete candidate for teams in Southeast Asia and beyond cutting per-task inference spend.

掘金本周最热@猫猫头啊6 sourcesSource

The release joins a crowded field of open-source coding agents from Chinese labs, including MiniMax Code, Zhipu's ZCode, Qwen Code, Kimi Code and DeepSeek's DSH, giving developers more MIT-licensed CLI options to self-host or benchmark. Since the Multi-Frame score comes from StepFun's own benchmark, cross-checking it against Terminal-Bench results from rival agents is the practical way to compare. The 75-day Plus subscription also offers a low-cost way to test Step 5 Preview before committing.

shao__meng@shao__mengSource

This is the first 600B-scale model from a Chinese company to be released with open weights, offering a significant alternative to other large models.

官方一手pandaily@[email protected] (Pandaily)Source

The model's cost is just 1/8 that of Anthropic Claude Opus 5, making it a more affordable option for developers and companies in the region.