Blogger benchmarks StepFun Preview vs Qwen 3.8 Max on Apple FY2025 analysis deck
CodeByPoonam · x · 2026-10-10
CodeByPoonam gave StepFun Preview and Qwen 3.8 Max the identical task: analyze Apple's FY2025 and produce a business analysis presentation. This post kicks off the side-by-side benchmark, with follow-ups detailing each model's output and quality differences.
Related event: StepFun Step 5 vs Qwen on Apple FY2025 deck task(2 posts)→
More from Models
- Google reportedly building Gemini 4.x, but blogger fears slow bureaucracy means it ships a generation behind frontier — haider1 · 2026-10-10
- Microsoft's open-source BitNet runs a 100B LLM on a single CPU with 1.58-bit weights — JafarNajafov · 2026-10-10
- Same $0.10/$0.50 price, 40% different bills: GPT-6 Luna beats Haiku 5.5 in real billing test — aakashgupta · 2026-10-10
- GPU kernel bench leaks: DeepSeek v4.1 flash beats GLM-5.3 and Haiku 5.5 — teortaxesTex · 2026-10-10
- Google's Gemini 4 "Carbon" Reportedly Matches Anthropic's Opus 5.5 on Coding — The Decoder · 2026-10-10
- Step 5 Preview makes clean slides, Qwen goes report-style in Apple deck showdown — CodeByPoonam · 2026-10-10