Real head-to-head · same prompt, one shot
Claude Opus 5 vs Kimi K3
The new Anthropic flagship — benched on all 45 one-shot builds the day it landed. vs Moonshot's 2.8T flagship — 1M context, tuned for long-horizon agent work.
Head-to-head verdict: Claude Opus 5 wins 22–21 with 7 ties.
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 Claude Opus 5 and Kimi K3, side by side, on 50 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.
Claude Opus 5 · Benched on all 45 GoldieBench tasks via API on release day, incremental deploys as scores landed.
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.
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 ↓
Claude Opus 5
Kimi K3
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Other
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.
Orbit
Sim
Claude Opus 5 9.0
·
Kimi K3 3.0
(+6.0)
· 3D N-body simulation
What I saw: Gorgeous 3D N-body sim with a glowing central star, 167 orbiting bodies with velocity trails, merges counter (12), tilted disks and companion cluster — genuine physics with softening, substeps, and merging, plus a polished camera/UI. Strong: visible dynamic simulation and beautif…
Galaxy
Sim
Claude Opus 5 8.8
·
Kimi K3 3.0
(+5.8)
· Gorgeous spiral vortex
What I saw: Stunning multi-arm spiral with a glowing core, gradient star coloring (gold→pink→blue), halo, and distant starfield — visually the strongest galaxy render, backed by rich swirl/orbit/zoom/supernova interaction. Only nit is FPS at 39, but the composition clearly matches or beats t…
Dogfight
Game
Claude Opus 5 8.4
·
Kimi K3 3.5
(+4.9)
· polished flight sim
What I saw: Gorgeous low-poly jet, layered HUD, radar with 4 bogeys, gradient sky and terrain with pull-up warning all render cleanly and read as a real dogfight sim; slightly short of top since the screenshot shows enemies only as radar dots rather than visible in-air combat/tracers, and sc…
Terrain
Visual
Claude Opus 5 8.3
·
Kimi K3 4.5
(+3.8)
What I saw: Strong island terrain with convincing height-based color ramp, sandy shores, snow-capped ridges, translucent water and a rich HUD/control panel; weak point is the flat black tree cones that read as silhouettes rather than lit foliage, slightly cheapening an otherwise polished, sh…
Solar
Sim
Claude Opus 5 8.6
·
Kimi K3 6.5
(+2.1)
· asteroid belt polish
What I saw: Strong 3D build: banded textured Sun with layered glow, all planets on inclined elliptical orbits, visible Earth+Moon, Saturn's rings, a convincing asteroid belt, plus real-data info panel and full follow/speed/scale controls. Minor knocks: labels are sparse (only some planets ta…
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.
Pool
Game
Kimi K3 8.1
·
Claude Opus 5 6.0
(+2.1)
What I saw: Renders a polished 3D pool table with proper rack, numbered balls, cue stick, aim line, pockets, HUD and physics/audio scaffolding — clearly shippable and on-brief. Weak points: the floating lamp shade looks unlit/misplaced and the rack triangle is slightly loose, keeping it just…
Arcade
Game
Kimi K3 8.4
·
Claude Opus 5 6.5
(+1.9)
· Neon Breakout Polish
What I saw: Gorgeous neon breakout that rendered cleanly with rainbow bricks, glowing paddle, ball trail, starfield and CRT scanlines, plus a full feature set (powerups, multiball, levels, audio, auto-demo). Very close to the field's best; loses a hair for being a well-trodden brief rather t…
Neonblaster
Game
Kimi K3 8.4
·
Claude Opus 5 6.8
(+1.6)
What I saw: Clean neon aesthetic with glowing title, HP diamonds, bomb button, star grid backdrop and a polished 'WAVE 1' banner render; source shows genuinely deep systems — 5 enemy types, bosses with named patterns, power-ups, procedural synth music with delay/compressor, screen-shake — bu…
Neoncity
Game
Kimi K3 8.7
·
Claude Opus 5 7.4
(+1.3)
· synthwave night drive
What I saw: 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 …
Doom
Game
Kimi K3 8.0
·
Claude Opus 5 6.8
(+1.2)
What I saw: Strong, polished raycaster with detailed procedural lava/metal wall textures, minimap, HUD, gun sprite and a distant medkit pickup visible — very shippable DOOM atmosphere. Weak point: no monster is visible in the rendered frame and HP already at 91, so the core 'monsters chase y…
Strengths & weaknesses I logged
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
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
Pricing & context — the spec sheet
| Spec | Claude Opus 5 | Kimi K3 |
|---|---|---|
| Vendor | Anthropic | Moonshot AI |
| Context window | 1,000,000 tokens | 1,048,576 tokens — a full codebase in working memory |
| Price | $5 / $25 per M | $3 / M in |
| Pricing detail | 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. | 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). |
| Release | 2026-07 | 2026-07-16 |
| Bench coverage | 50/50 scored · avg 8.27/10 | 50/50 scored · avg 7.89/10 |
The verdict — which should you pick?
Across 50 scored shared tasks, Claude Opus 5 averaged 8.27/10, beating Kimi K3's 7.89/10 by 0.38 points. Pick Claude Opus 5 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 Claude Opus 5 and Kimi K3 both into the Agent Operating System and dispatch each from the kanban by task type — hardest agentic builds → Claude Opus 5, long-horizon agent runs → Kimi K3. That's the same setup I run for the 4,000+ founders inside the AI Profit Boardroom.
FAQ — Claude Opus 5 vs Kimi K3
Which is better, Claude Opus 5 or Kimi K3?
On Goldie Bench, Claude Opus 5 averages 8.27/10 across the shared tasks, with 13 gold, 7 silver, 5 bronze overall. Kimi K3 averages 7.89/10, with 8 gold, 4 silver, 7 bronze. Claude Opus 5 wins the head-to-head 22–21.
How much does Claude Opus 5 cost vs Kimi K3?
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. 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).
What's the context window for Claude Opus 5 vs Kimi K3?
Claude Opus 5 has a 1,000,000 tokens context window. Kimi K3 has a 1,048,576 tokens — a full codebase in working memory context window.
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.
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.
How does Goldie Bench score Claude Opus 5 vs Kimi K3?
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:
Claude Opus 5 vs Fusion Kimi K3 vs Fusion Claude Opus 5 vs Hermes MoA Kimi K3 vs Hermes MoA Claude Opus 5 vs GPT-5.6 Sol Kimi K3 vs GPT-5.6 Sol Claude Opus 5 vs Claude Fable 5 Kimi K3 vs Claude Fable 5Full model pages: Claude Opus 5 · Kimi K3 · 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