Real head-to-head · same prompt, one shot
Kimi K3 vs Claude Opus 5
Moonshot's 2.8T flagship — 1M context, tuned for long-horizon agent work. vs The new Anthropic flagship — benched on all 45 one-shot builds the day it landed.
Head-to-head verdict: Kimi K3 wins 11–1 with 1 tie.
What I tested — same prompt, two models
I run the same fixed prompt set through every new model the day it drops — same string, one shot, single HTML file out — and I score the result 0–10 on whether it ran, how close it hit the brief, and how good it looked. Below is what came out when I gave the exact same prompts to Kimi K3 and Claude Opus 5, side by side, on 22 shared tasks inside the Agent Operating System.
Both models were given identical prompts inside the Agent Operating System — no help, no iteration, no "best of N" tricks. I run each prompt once, save the HTML file the model produces, and score it 0–10 on whether it ran, how close it hit the brief, and how good it looked. The scoring is mine. The verdicts below are pulled from my source comparison guides at agentos.guide where I publish every score and the reasoning behind it.
Kimi K3 · Wired into the Agent OS as the `kimi-k3` Hermes profile and a K3 speed-toggle in the Kimi Code tab — used for long unattended agent runs where a slow-but-right model beats a fast-but-forgetful one.
Claude Opus 5 · Benched on all 45 GoldieBench tasks via API on release day, incremental deploys as scores landed.
Side-by-side on 50 shared tasks
Click any cell to play that model's actual one-shot attempt. Medals are derived from my 0–10 scores per task (highest = 🥇, second = 🥈, third = 🥉).
Task ↓
Kimi K3
Claude Opus 5
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
— not attempted —
Other
— not attempted —
Where Kimi K3 beat Claude Opus 5
The tasks where I gave Kimi K3 a higher 0–10 score on the same prompt — with the actual commentary from my source guides.
Neonracer
Game
Kimi K3 8.6
·
Claude Opus 5 2.0
(+6.6)
· Synthwave sunset racer
What I saw: Gorgeous, fully-on-brief synthwave scene — retro sun, wireframe mountains, neon grid, dashed lanes and glowing vapor-trail particles behind the car all render crisply with polished HUD. Only minor nitpick is the car model reads a touch plain, but visually this matches/beats the f…
Game
Game
Kimi K3 8.4
·
Claude Opus 5 2.5
(+5.9)
· neon 3D runner
What I saw: Strong, polished 3D synthwave endless runner with Three.js—glowing player orb, neon rails, moving pylons, starfield sun, and a clean HUD (score/best/lives/speed) all render beautifully and on-brief. Deducts slightly for being a familiar lane-runner concept, but the execution and …
Gtafoot
Game
Kimi K3 8.2
·
Claude Opus 5 2.5
(+5.7)
What I saw: Strong, atmospheric neon night city with a well-composed third-person character, clean HUD (wanted stars, health, ammo, minimap, money) and full weapon/cover/pedestrian systems in source; visually polished and clearly on-brief, but the emissive-window city and blocky avatar feel …
Crypt
Game
Kimi K3 7.4
·
Claude Opus 5 2.0
(+5.4)
What I saw: Renders a clean, atmospheric brick corridor with polished title typography, a working minimap, and solid HUD framing, but the scene reads cool-blue and under-lit rather than warmly torch-lit — no visible flames or orange glow undercut the core brief, keeping it strong-but-generic…
Flightsim
Game
Kimi K3 8.2
·
Claude Opus 5 3.0
(+5.2)
What I saw: Strong, polished render with a clean 3D plane on a proper runway, full HUD (compass ribbon, artificial horizon, IAS/ALT gauges, throttle slider) and nice terrain/hangar/windsock props; minor blemish is the 'VS NaN' readout indicating an uninitialized vertical-speed calc, which ke…
Where Claude Opus 5 beat Kimi K3
The tasks where I gave Claude Opus 5 a higher 0–10 score on the same prompt — with the actual commentary from my source guides.
Dogfight
Game
Claude Opus 5 8.4
·
Kimi K3 3.5
(+4.9)
· polished 3D flight sim
What I saw: Gorgeous detailed player jet, full flight HUD, functional radar showing 4 bogeys, terrain warning, and afterburner/boost systems all read as a shippable 3D dogfighter. Slightly held back because the screenshot shows no visible enemy aircraft in view or active combat/tracers, leav…
Strengths & weaknesses I logged
Kimi K3
Strengths
- Launch-day benchmarks put it around the Fable/Sol tier, with Terminal Bench (agentic terminal-driving) the standout
- 1M-token context verified on this bench's needle test: exact recall from 162k tokens of noise in 18s
- One-shot builds run long but land complete — its first bench game (13.4 min of thinking, 30,880 tokens) playtested with zero JS errors
- Included in the Kimi coding plan — frontier tier without a new bill
Trade-offs
- Slow on hard tasks — early testers report up to ~35 minutes at max reasoning; this bench saw 13+ minute single builds
- Launch-day rate limits on OpenRouter (429s) — the coding-plan endpoint was the reliable route
- Self-reports as K2.7 if you ask it — verify the served model via the API response, not the model's word
Claude Opus 5
Strengths
- Frontier-class coding + agentic reasoning (Claude 5 family)
- 1M-token context — reads an entire codebase in one call
- Benched here with skill-infused game prompts the day of release
Trade-offs
- Premium pricing ($5/$25 per M) — route the everyday 90% to cheaper lanes
- Reasoning-by-default eats token budgets unless tuned per call
Pricing & context — the spec sheet
| Spec | Kimi K3 | Claude Opus 5 |
|---|---|---|
| Vendor | Moonshot AI | Anthropic |
| Context window | 1,048,576 tokens — a full codebase in working memory | 1,000,000 tokens |
| Price | $3 / M in | $5 / $25 per M |
| Pricing detail | 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). | Anthropic's brand-new flagship — the first Opus of the Claude 5 family, with a 1M-token context window. Benched via API the day it dropped; game tasks use our skill-infused AAA build prompts. |
| Release | 2026-07-16 | 2026-07 |
| Bench coverage | 50/50 scored · avg 7.89/10 | 13/22 scored · avg 5.60/10 |
The verdict — which should you pick?
Across 13 scored shared tasks, Kimi K3 averaged 7.94/10, beating Claude Opus 5's 5.60/10 by 2.34 points. Pick Kimi K3 when the build has to ship on the first prompt and you can afford the trade-offs in the comparison below.
If you only run one of these inside your stack, the head-to-head average above is the call. If you can run both, my honest play is to wire Kimi K3 and Claude Opus 5 both into the Agent Operating System and dispatch each from the kanban by task type — long-horizon agent runs → Kimi K3, hardest agentic builds → Claude Opus 5. That's the same setup I run for the 4,000+ founders inside the AI Profit Boardroom.
FAQ — Kimi K3 vs Claude Opus 5
Which is better, Kimi K3 or Claude Opus 5?
On Goldie Bench, Kimi K3 averages 7.94/10 across the shared tasks, with 9 gold, 7 silver, 5 bronze overall. Claude Opus 5 averages 5.60/10, with 0 gold, 0 silver, 1 bronze. Kimi K3 wins the head-to-head 11–1.
How much does Kimi K3 cost vs Claude Opus 5?
Kimi K3: 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). Claude Opus 5: Anthropic's brand-new flagship — the first Opus of the Claude 5 family, with a 1M-token context window. Benched via API the day it dropped; game tasks use our skill-infused AAA build prompts.
What's the context window for Kimi K3 vs Claude Opus 5?
Kimi K3 has a 1,048,576 tokens — a full codebase in working memory context window. Claude Opus 5 has a 1,000,000 tokens context window.
When should I pick Kimi K3 over Claude Opus 5?
Pick Kimi K3 for: long-horizon agent runs; whole-repo context work; terminal-driving agents. The trade-off is the weaknesses we logged on the bench: Slow on hard tasks — early testers report up to ~35 minutes at max reasoning; this bench saw 13+ minute single builds; Launch-day rate limits on OpenRouter (429s) — the coding-plan endpoint was the reliable route; Self-reports as K2.7 if you ask it — verify the served model via the API response, not the model's word.
When should I pick Claude Opus 5 over Kimi K3?
Pick Claude Opus 5 for: Hardest agentic builds; Whole-repo reasoning; Frontier one-shots. The trade-off is the weaknesses we logged on the bench: Premium pricing ($5/$25 per M) — route the everyday 90% to cheaper lanes; Reasoning-by-default eats token budgets unless tuned per call.
How does Goldie Bench score Kimi K3 vs Claude Opus 5?
Every demo on this page was built by Julian Goldie inside the Agent Operating System — same fixed prompt for both models, one shot, single HTML file out. Each result gets a 0–10 score on whether it ran, how close it hit the brief, and how good it looked. The highest score on each task gets gold; second gets silver; third gets bronze. See methodology for full provenance.
Related comparisons
Other head-to-heads using the same scoring system:
Kimi K3 vs Fusion Claude Opus 5 vs Fusion Kimi K3 vs Hermes MoA Claude Opus 5 vs Hermes MoA Kimi K3 vs GPT-5.6 Sol Claude Opus 5 vs GPT-5.6 Sol Kimi K3 vs Claude Fable 5 Claude Opus 5 vs Claude Fable 5Full model pages: Kimi K3 · Claude Opus 5 · back to the leaderboard
The same stack Julian uses
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.
4,000+founders
258documented wins
38countries
$59/momonthly