The "which should I use?" chooser
Best for…
For each task, the current best pick — with a one-line why and the date we last affirmed it. AI models and smart-home devices, side by side.
Newest isn't always best. A pick is the current choice as of its date — not whatever shipped most recently. Every pick is dated and tracked over time.
AI models
The current pick per task across the frontier and open-weight model families.
Cheap / budget
as of June 1, 2026- ①
Gemini 2.5 Flash-LiteGemini 2.5 Flash-Lite — $0.10/$0.40 per 1M with a 1M-token context; the budget workhorse.
- ②
GPT-5.4 nanoGPT-5.4 nano — cheapest model with GPT-5-generation capability ($0.10/$0.40), for classification/routing.
- ③
Ministral 3BMinistral 3B — the cheapest API option anywhere at $0.04/$0.04 per 1M; open weights.
- ①
Claude Opus 4.8Claude Opus 4.8 — reliability-focused flagship, 4x less likely than 4.7 to let its own code flaws pass.
- ②
Claude Sonnet 4.6Claude Sonnet 4.6 — Opus-level coding quality at $3/$15, 79.6% SWE-bench Verified.
- ③
Gemini 3.5 FlashGemini 3.5 Flash — beats Gemini 3.1 Pro on coding benchmarks at ~25% lower cost.
Image generation
as of June 1, 2026- ①
AI Image & VideoThe AI Image & Video section tracks the current image-generation leaders across providers.
- ②
AuroraxAI Aurora — image generation built into the Grok interface.
Local / private
as of June 1, 2026- ①
Qwen3-32BQwen3-32B — leading open-weight (Apache 2.0) mid-size general model with a configurable thinking mode; runs locally.
- ②
Llama 3.3 70BLlama 3.3 70B — matches Llama 3.1 405B quality at a fraction of the cost; the community default for self-hosted text.
- ③
Mistral Small 4Mistral Small 4 — unified open-weight (Apache 2.0) reasoning + vision + coding model in one small package.
Long context
as of June 1, 2026- ①
Llama 4 ScoutLlama 4 Scout — 10M-token context, the longest of any released model; best needle-in-a-haystack retrieval.
- ②
Gemini 3.1 ProGemini 3.1 Pro — 2M-token context, the largest production context window of any hosted API.
Real-time / web
as of June 1, 2026- ①
Sonar ProPerplexity Sonar Pro — highest-quality cited answers grounded in live web search.
- ②
Grok 4.3Grok 4.3 — native real-time X/web access with strong agentic tool-calling, $1.25/$2.50 per 1M.
Reasoning
as of June 1, 2026- ①
GPT-5.5 ProGPT-5.5 Pro — maximum-reasoning-depth variant for research-grade problems.
- ②
Gemini 2.5 ProGemini 2.5 Pro — proven Deep Think reasoning with a 1M-token context.
- ③
Grok 4.20Grok 4.20 — extended-reasoning Think Mode with the strongest hallucination resistance in the Grok family.
Video generation
as of June 1, 2026- ①
AI Image & VideoThe AI Image & Video section tracks the current video-generation leaders across providers.
- ①
GPT-4oGPT-4o — native audio/voice model; still the API workhorse for real-time voice tasks.
- ②
GPT-4o miniGPT-4o mini — cheap native-audio model ($0.15/$0.60) for budget voice apps.
Writing
as of June 1, 2026- ①
Claude Opus 4.8Claude Opus 4.8 — the frontier Anthropic flagship most consistently preferred for long-form prose and editorial voice.
- ②
GPT-5.5GPT-5.5 — strong all-round writer with a 1M-token context, close behind on draft quality.
Smart home
The current pick per task across hubs, cameras, and the connected-home stack.
Best for accessibility
as of June 1, 2026- ①
Smart HomeVoice-first hubs and presence automation make the smart home a powerful accessibility tool — start with the Smart Home guide.
Best smart-home hub
as of June 1, 2026- ①
Aqara Hub M3Aqara Hub M3 — Matter controller + Thread border router + Zigbee 3.0 in one box; the lowest-friction multi-ecosystem hub.
- ②
Echo HubAmazon Echo Hub — purpose-built dashboard with Matter + Zigbee + Thread baked in for Alexa households.
- ③
SmartThings StationSmartThings Station — combo Qi charger + Matter / Thread / Zigbee hub at a small footprint.
Picks are editorial judgements, each stamped with the date it was last affirmed. Disagree? Tell us — the point is to keep these current.