Kimi K2.7 · No-Think

Reference benchmarks for Kimi K2.7 · No-Think

These are external benchmarks I pulled from the source comparison guides on agentos.guide — SWE-bench Verified, DRACO, Kilo plan rubric, build-time measurements, vendor-reported coding scores. They are not goldiebench medal scores (those come only from same-prompt one-shot creative coding tasks in the matrix). I surface them here so the spec sheet for Kimi K2.7 · No-Think is honest about what's measured.

What is Kimi K2.7 · No-Think?

Kimi K2.7 · No-Think is the Moonshot AI frontier model with a 256,000 tokens context window, released 2026-06. Tagline: Pure execution mode — no chain of thought.. Official source: kimi.com.

Pricing detail. Same flat-rate plan as standard Kimi K2.7 — No-Think disables the chain-of-thought layer at runtime. Vendor: Moonshot AI (moonshot.ai).

How I use it inside the Agent OS. Reserved for templated transforms where the plan is already in the prompt — the model just executes.

What I built with Kimi K2.7 · No-Think

Every model on Goldie Bench gets the same fixed prompt set — one shot, single HTML file out — and I score the result 0–10 inside the Agent Operating System. Here's what Kimi K2.7 · No-Think shipped on the bench: 47 one-shot demos across 256,000 tokens of context. Of those, 0 are scored against the field with my honest 0–10 from the source guides at agentos.guide.

Best for

• Templated transforms where the plan is in the prompt
• Batched code generation jobs
• Workflows where you want the model to stop second-guessing

Compare Kimi K2.7 · No-Think against every other model

Every head-to-head featuring Kimi K2.7 · No-Think. Verdicts shown for scored pairs.

See all 66 comparisons across every model →

Quick pill index

Direct comparisons against every other scored model on the bench:

Read more on agentos.guide: /kimi-modes-head-to-head

Kimi K2.7 · No-Think — frequently asked