GoldieBench deep dive
Kimi K3's full benchmark breakdown.
Moonshot's 2.8T flagship — 1M context, tuned for long-horizon agent work. Every number below is either one of my own judged one-shot builds - playable on this site - or an outside result with its source linked. Nothing display-only, nothing vibes.
01 · The headline numbers
02 · Every benchmark, bar by bar
All 50 scored tasks, best first. Hover for the judge's comment; click through for every model's build on that task. Or overlay other models in the interactive graphs.
03 · Where it wins - with the judge's own words
“Gorgeous real geodesic raytracing with a properly lensed accretion disk wrapping over the top, convincing Doppler asymmetry, photon-ring glow, and a rich nebula starfield backdrop; polished typography and clean UI push it to the top of the field. Minor stat overlap at bottom-left ('photon sphe' clipped by hint pill) is the only blemish.”
“Gorgeous, textbook-quality WebGL fluid sim with rich swirling dye, added particle sparkle, and polished UI (gradient title, hint pill, control buttons) — the vorticity/pressure-solve pipeline and half-float fallback handling are all correct and shippable; only minor knock is the visual is close to the well-known Pavel Dobryakov reference.”
“Nails every synthwave trope beautifully — banded sunset, receding neon perspective grid, layered mountains, glowing gradient title, floating wireframe solids, starfield, scanlines/vignette, and generative WebAudio music. Highly polished and cohesive; a clear task winner.”
“Gorgeous flowing volumetric aurora ribbons with convincing fbm noise, layered mountains, spruce silhouettes, moon, stars and a shooting star make a genuinely atmospheric scene; the elegant typography, palette switcher and vignette give it a shippable polish that edges past the field's best.”
“Gorgeous on-brief cyberpunk drive: glowing multicolor building windows, cyan/magenta neon road edges, a synthwave sunset moon down the vanishing point, and clean HUD with speed/distance—strongly atmospheric and polished. Minor nitpicks are the somewhat sparse traffic and generic sign legibility, but the render clearly nails the vaporwave neon-city vibe at a task-winning level.”
04 · Where it struggles - quoted, not hidden
Boards that hide the weak rows are brochures. These are Kimi K3's lowest scored builds, verdicts unedited:
“The UI chrome (title, hint, control panel) renders beautifully, but the entire simulation canvas is empty black — no star, planets, asteroid belt, or trails appear, so the core N-body simulation failed to render. Strong styling can't compensate for a non-functioning main feature.”
“The UI chrome (title, buttons, hint bar) renders beautifully with polished gradient typography, but the core galaxy particle system is completely absent — the canvas is empty black and '—PARTICLES' shows the count never populated, indicating the Three.js render failed or hung. A stylish shell around a non-functional centerpiece.”
“HUD, title screen, and crosshair are polished and on-brief, but the 3D scene failed to render — the background is pure black despite code defining a sky dome, ground, clouds, and planes, so no actual dogfight/flight is visible.”
“Strong scaffolding — nice sky gradient, water, clouds, sand beaches, instanced trees, and clean UI — but the terrain interior renders almost entirely black, indicating a broken lighting/normals or vertex-color issue that dominates the screenshot. The visible flaw undercuts an otherwise polished procedural island explorer.”
05 · Category breakdown vs the whole field
Games (23 tasks)
Others (3 tasks)
Pages (3 tasks)
Sims (12 tasks)
Visuals (9 tasks)
06 · Outside signals - every row sourced
My bench measures one thing: judged one-shot builds. These outside rows measure other things - kept separate, never blended into the GoldieBench average, every value linked to where it comes from.
Vendor-published numbers
| Benchmark | Result | Source |
|---|---|---|
| Parameters | 2.8T MoE - 16 of 896 experts active (corrected from the launch-day 2.5T estimate) | www.kimi.com |
| Context window | 1,048,576 tokens, flat pricing across it | www.kimi.com |
| API pricing | $3.00/M input (cache-miss) - $0.30/M cached - $15.00/M output | platform.kimi.ai |
| Terminal-Bench 2.1 | 88.3 (vendor launch table) | www.kimi.com |
| FrontierSWE | 81.2 (vendor launch table) | www.kimi.com |
| BrowseComp | 91.2% with 300K-token compaction - 90.4% raw 1M window | www.kimi.com |
Independent evaluations
| Benchmark | Result | Source |
|---|---|---|
| LMArena Frontend Code Arena | #1 debut - 1679 Elo across 1,757 votes - a 17-place jump over K2.6 | x.com |
| LMArena main text board | 1486 Elo across 3,026 votes (coding 1530, hard prompts 1506) | x.com |
| Artificial Analysis indices | Intelligence 57.11 - Coding 76.24 - Agentic 50.07 | artificialanalysis.ai |
| Artificial Analysis runtime | 62 output tok/s - 1.99s to first token - ~$0.94 per task | x.com |
| Vals Index v1.2 | 74.7 - Terminal-Bench 2.1 hosted view 80.899 | www.vals.ai |
From the source guides
| Measure | Result | Source guide |
|---|---|---|
| Launch-day community benchmarks | ~Fable/Sol tier; Terminal Bench the standout | /kimi-k3-machine |
The posts themselves
Arena announces K3's #1 debut on the Frontend Code Arena: @arena
Artificial Analysis publishes its full independent K3 evaluation: @ArtificialAnlys
The launch-day benchmark drop that framed K3 as ~Fable/Sol tier: @synthwavedd
07 · Head-to-head records
08 · Methodology + honest limits
Every GoldieBench score is a one-shot, single-file build from an identical prompt - no retries, no hand-fixing - rendered for real, screenshotted, and scored 0-10 by one judge model on one rubric across the whole field. Failures score as failures. What this bench does NOT measure: multi-turn agent work, long-context recall, or API latency - that is what the sourced outside rows are for. Full method: /methodology.
Frequently asked questions
01How does Kimi K3 perform on GoldieBench?
Kimi K3 averages 7.89/10 across 50 scored one-shot build tasks, ranking #9 of 17 ranked frontier models, with 11 task golds, 8 silvers and 8 bronzes. Every score is a real judged build you can open and play on this site.
02What is Kimi K3 best at?
Its strongest scored build is Blackhole at 9.0/10. By category it averages Game 8.1, Other 8.3, Page 7.9, Sim 7.2, Visual 8.1 on the bench.
03How much does Kimi K3 cost?
Launched July 16, 2026. 2.8T-param MoE (Moonshot's quickstart corrected the circulating 2.5T estimate). $3/M input on OpenRouter at launch; included at no extra cost in the Kimi coding plan (`k3` on the coding endpoint).
Source ledger
- 01Official vendor site: kimi.comwww.kimi.com
- 02Parameterswww.kimi.com
- 03API pricingplatform.kimi.ai
- 04LMArena Frontend Code Arenax.com
- 05Artificial Analysis indicesartificialanalysis.ai
- 06Artificial Analysis runtimex.com
- 07Vals Index v1.2www.vals.ai
- 08Launch-day community benchmarksagentos.guide
- 09The launch-day benchmark drop that framed K3 as ~Fable/Sol tierx.com
Every model's breakdown
Run this stack yourself.
Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.