SOTA models

Registry v1 · updated 2026-07-06. This page is generated from docs/data/sota-models.json, the single source of truth for which models smithers configures by default. A daily research job checks every provider for new GA models and opens a PR here when the state of the art moves; bunx smithers-orchestrator update picks the changes up on your machine, and re-running bunx smithers-orchestrator init refreshes installed workflows to the new defaults.

​

Badges

Each badge names the single best model for that job right now.

​

Role defaults

The fable-sandwich tiers (see the workflow optimization guide) resolve to these ids:

​

Anthropic

​

Claude Fable 5 (claude-fable-5)

Best orchestrator · Smartest reviewer · Smartest coder · state of the art · engines: claude, opencode · roles: orchestrator, planning, review, smart Anthropic’s Mythos-class frontier model, the first of the Claude 5 family. The strongest model available for planning, code review, and orchestrating other agents, which is why it sits at both ends of the fable sandwich: it writes the plan, delegates implementation, then reviews the result.

​

Claude Opus 4.8 (claude-opus-4-8)

current · engines: claude, opencode · roles: smart Anthropic’s Opus tier. Still a top-shelf generalist and the always-present fallback behind Fable in the smart, planning, and review pools.

​

Claude Sonnet 5 (claude-sonnet-5)

current · released 2026-06-29 · engines: claude, opencode · roles: implement, cheapFast The newest Sonnet: fast, cheap, 1M context. The guaranteed implementer fallback in the fable sandwich and the default cheapFast Claude.

​

Claude Haiku 4.5 (claude-haiku-4-5)

current · engines: claude, opencode Anthropic’s cheapest tier, for high-volume summarization and classification where even Sonnet is overkill.

​

OpenAI

​

GPT-5.5 (gpt-5.5)

state of the art · engines: codex, pi · roles: implement, smart OpenAI’s GA flagship and the Codex CLI default. The implementation workhorse in the middle of the fable sandwich. With ChatGPT auth use the id gpt-5.5 exactly (gpt-5.5-codex and gpt-5.3-codex are deprecated in Codex).

​

GPT-5.4 (gpt-5.4)

current · engines: codex, pi The previous OpenAI flagship. Still solid for professional work when gpt-5.5 quota is tight.

​

GPT-5.4 mini (gpt-5.4-mini)

current · engines: codex, pi · roles: cheapFast OpenAI’s fast, efficient tier. The default cheap OpenAI model, including via OpenRouter (openai/gpt-5.4-mini).

​

GPT-5.3-Codex-Spark (gpt-5.3-codex-spark)

Fastest coding · state of the art · released 2026-02-12 · engines: codex · roles: realtime OpenAI’s first real-time coding model: 1000+ tokens per second on dedicated Cerebras hardware while staying genuinely capable. Research preview, ChatGPT Pro only. Reach for it when iteration latency matters more than depth.

​

Google

​

Gemini 3.5 Flash (gemini-3.5-flash)

Best at UI · Fast & cheap · state of the art · released 2026-05-19 · engines: antigravity · roles: ui, implement, cheapFast Google’s best price-to-performance model and the best model for UI work: near-Pro intelligence at Flash speed and cost, 1M context, and it beats Gemini 3.1 Pro on coding and agentic benchmarks while running roughly 4x faster. The default Gemini in smithers.

​

Gemini 3.1 Pro (gemini-3.1-pro-preview)

current · engines: antigravity Google’s Pro tier (still preview). Superseded for coding and agentic work by Gemini 3.5 Flash; keep it for long-horizon reasoning where Pro depth wins.

​

Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)

current · engines: antigravity Frontier-class performance at a fraction of the cost. The floor of the Gemini lineup for bulk, low-stakes calls.

​

Moonshot AI

​

Kimi K2.7-Code (kimi-k2.7-code)

Best value coding · state of the art · released 2026-06-12 · engines: kimi · roles: implement, cheapFast Moonshot’s most capable coding model and the best coding value on the market: 256k context, roughly 30% fewer reasoning tokens than K2.6, strong instruction-following in long contexts. The default Kimi in smithers; the -highspeed variant trades a little quality for ~180 tok/s.

​

Kimi K2.7-Code High-Speed (kimi-k2.7-code-highspeed)

current · engines: kimi · roles: realtime The high-throughput K2.7-Code variant, around 180 tokens per second. The open-weights answer to Codex-Spark for latency-sensitive loops.

​

Kimi K2.6 (kimi-k2.6)

Best open source · current · released 2026-04-20 · engines: kimi · roles: research Moonshot’s open-source (modified MIT) trillion-parameter MoE flagship: native multimodal, agent swarms up to 300 sub-agents, up to 13 hours of continuous coding. Ties GPT-5.5 on SWE-Bench Pro at roughly 80% lower cost. The strongest model you can self-host.

​

Deprecated ids

Rewrite these on sight; the daily research job does the same sweep mechanically.

​

Update policy

• Only GA (generally available) models enter the registry. Limited previews (e.g. GPT-5.6 Sol/Terra/Luna) wait until they ship for real.
• Research previews with real availability (e.g. gpt-5.3-codex-spark on ChatGPT Pro) may enter with status sota for their niche, noted in the description.
• No floating aliases (kimi-latest, *-latest). Pin concrete ids so a provider-side model swap cannot bypass this registry.
• Every badge names exactly one model. A new badge holder demotes the old one in the same change.
• Any change to models bumps version by exactly 1 and refreshes updatedAt.
• Deprecated entries keep their replacedBy id for one release so sweeps know what to rewrite, then get deleted.