Get the Agent OS + join 4,000+ founders inside the AI Profit Boardroom → Join AIPB ($59/mo)
Anthropic

Claude Opus 5.5

Anthropic's Opus 5.5 — benched on all 50 one-shot builds, every game playtested.

Context1,000,000 tokens
Pricing$4 / $20 per M
Tasks tested50
Avg score7.57/10 average
Medals🥇0 🥈0 🥉1
Release2026-09
Official vendor source
Claude Opus 5.5 is built by Anthropic — see the vendor's own product page, pricing, and docs at anthropic.com/claude.
Visit anthropic.com/claude →

What is Claude Opus 5.5?

Claude Opus 5.5 is the Anthropic frontier model with a 1,000,000 tokens context window, released 2026-09. Tagline: Anthropic's Opus 5.5 — benched on all 50 one-shot builds, every game playtested.. Official source: anthropic.com/claude.

Pricing detail. Anthropic's Opus 5.5 — 1M-token context, listed at $4 input / $20 output per million tokens. Benched through a Claude subscription; game tasks use our skill-infused AAA build prompts.

How I use it inside the Agent OS. Benched on all 50 GoldieBench tasks via a Claude subscription: one-shot builds, real renders, pixel-diff playtests on every game, then vision-judged.

What I built with Claude Opus 5.5

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 Claude Opus 5.5 shipped on the bench: 50 one-shot demos across 1,000,000 tokens of context. Of those, 50 are scored against the field with my honest 0–10 from the source guides at agentos.guide.

Strengths

  • Frontier-class coding + agentic reasoning (Claude 5 family)
  • 1M-token context — reads an entire codebase in one call
  • All 50 one-shot builds rendered with zero console errors; all 23 games passed the input playtest

Trade-offs

  • Premium pricing ($4/$20 per M) — route the everyday 90% to cheaper lanes
  • One-shot builds can still ship logic bugs (e.g. a doom kill counter that miscounts)

Best for

  • Hardest agentic builds
  • Whole-repo reasoning
  • Frontier one-shots

Every demo by Claude Opus 5.5

50 live demos, sorted by category. Click any tile to play the actual one-shot result. Verdicts and 0–10 scores are pulled from the source guides where I posted them publicly.

Claude Opus 5.5 one-shot build of Crypt — GoldieBench AI benchmark screenshot▶ LIVE
Crypt
Game
Convincing torch-lit crypt: textured stone walls, arch, cobwebs, glowing held torch and a detailed first-person sword, with a clean HUD. No undead visible mid-play and the lighting is a bit evenly warm, so it's strong but not above the field's 9.0.
Claude Opus 5.5 one-shot build of Dragonrealm — GoldieBench AI benchmark screenshot▶ LIVE
Dragonrealm
Game
Charming frozen world: snowfall, moon, snow-capped pines, ruins arch, a modelled armoured hero with a drawn sword, a wraith enemy, and a cohesive HP/ST/compass/dragon HUD. Low-poly and stylised rather than epic, and the fog-flattened snow reads a little bland, so it falls short of the 9.0 field best.
Claude Opus 5.5 one-shot build of Doom — GoldieBench AI benchmark screenshot▶ LIVE
Doom
Game
Solid raycaster chrome (shotgun viewmodel, minimap with demons, cohesive HUD), but the mid-play frame is a red-washed, noisy wall maze with no demon on screen. The known splice bug breaks the KILLS/DEMONS LEFT count and the win check after the first kill.
Claude Opus 5.5 one-shot build of Racing — GoldieBench AI benchmark screenshot▶ LIVE
Racing
Game
Characterful desert circuit with a numbered muscle car, a buggy raider, grandstand, kerbs, cacti and a track minimap in a tidy HUD. A heavy red damage vignette and washed-out haze flatten the frame, so it reads well below the field's best.
Claude Opus 5.5 one-shot build of Skyrim — GoldieBench AI benchmark screenshot▶ LIVE
Skyrim
Game
First-person with sword, shield, magicka/health/stamina bars, compass and foes, so the systems are there. Visually it's flat: plain green hills under dusk haze, a huge untextured brown shield disc covering a third of the screen, and a stark black-and-white sword, with little atmosphere and no enemies in view.
Claude Opus 5.5 one-shot build of Twilightvale — GoldieBench AI benchmark screenshot▶ LIVE
Twilightvale
Game
EYEBALL GATE: the minimap sits over the title and HP/stamina/XP labels. The camera clips into a house wall, the scene is washed-out lavender-white, and the boxy wolf reads crude, though there is a quest tracker, a robed hero and rain.
Claude Opus 5.5 one-shot build of Voxelcraft — GoldieBench AI benchmark screenshot▶ LIVE
Voxelcraft
Game
Hotbar, hearts, clock and a night-mob system exist, but the mid-play frame is crude: big flat-coloured blocks with no visible texture, the camera jammed against a tree trunk and leaves, and a cramped, hard-to-read view. Also carries the known pre-dusk burning-zombie glow bug.
Claude Opus 5.5 one-shot build of Gtafoot — GoldieBench AI benchmark screenshot▶ LIVE
Gtafoot
Game
Playable third-person city with a jointed voxel character, crate cover, a taxi, lit windows, a round minimap, wanted stars and a clean ammo/kills HUD. The lighting is flat and pastel, there are no pedestrians or action in the mid-play frame, and the boxy low-poly look is short of GTA atmosphere.
Claude Opus 5.5 one-shot build of Gtadrive — GoldieBench AI benchmark screenshot▶ LIVE
Gtadrive
Game
All the open-city parts are in place: windowed tower canyons under a sunset sky, cop cars already chasing, wanted stars, cash goal, minimap and steal-car key. A huge foreground streetlamp and blotchy pink light cones clutter the view, and the gun turret on the car is a generic touch.
Claude Opus 5.5 one-shot build of Aipbpromo — GoldieBench AI benchmark screenshot▶ LIVE
Aipbpromo
Page
Auto-playing 32s timeline with scene markers, scrub bar and a synthwave grid backdrop is well built. But the captured hook frame is mostly empty: one tilted word and a faint 'Content' pill, with no brand, stats or product visuals, so it doesn't feel like a cinematic ad.
Claude Opus 5.5 one-shot build of Parachute — GoldieBench AI benchmark screenshot▶ LIVE
Parachute
Game
The exit moment works: a detailed plane, an articulated skydiver, altitude/descent HUD, distance-to-clearing compass and a deploy prompt. The mid-play frame is mostly empty grey-blue sky, and no jungle or clearing is visible yet.
Claude Opus 5.5 one-shot build of Flightsim — GoldieBench AI benchmark screenshot▶ LIVE
Flightsim
Game
Covers the whole brief: a real takeoff roll, heading tape, attitude ball, airspeed/altitude/VS readouts, gear, graded landings and crash states. The airfield has a hangar and tower and the prop plane is detailed. The frame is still on the runway and the sun glare blows out the top-left; the bolted-on combat adds little.
Claude Opus 5.5 one-shot build of Arcade — GoldieBench AI benchmark screenshot▶ LIVE
Arcade
Game
Rich 3D neon snake arena with good lighting and enemies, but the HUD breaks: a global canvas{position:fixed;left:0;top:0} rule pulls the minimap into the top-left over the HEALTH/BOOST panel (overlapping UI, capped at 6.0). Snake-turned-wave-shooter also drifts from the classic arcade brief, and the foreground fence posts block the view.
Claude Opus 5.5 one-shot build of Dogfight — GoldieBench AI benchmark screenshot▶ LIVE
Dogfight
Game
Bright, well-lit low-poly world (lakes, forests, village, runway) with a decent jet model and a clean hull/boost/throttle HUD plus radar. The frame reads more like a flight sim than a fight: enemies are specks, the score is 0, and there is an odd flat orange disc in the scene.
Claude Opus 5.5 one-shot build of Dragonflight — GoldieBench AI benchmark screenshot▶ LIVE
Dragonflight
Game
EYEBALL GATE: the radar disc sits on top of the score panel and hides the SCORE digits and the RINGS/FOES labels. Behind that, the atmospheric pink low-poly world, the winged dragon and the fire-breath bloom look good, but no neon rings show in the mid-play frame.
Claude Opus 5.5 one-shot build of Game — GoldieBench AI benchmark screenshot▶ LIVE
Game
Game
Emberfall Vale is a cohesive low-poly third-person action game with an armoured knight, slime and goblin enemies, runestones, a minimap and a clean HUD. Well made, but a generic fantasy-arena take with a fairly bland open field.
Claude Opus 5.5 one-shot build of Neonblaster — GoldieBench AI benchmark screenshot▶ LIVE
Neonblaster
Game
EYEBALL GATE: the radar disc is drawn over the NEON BLASTER logo and the HULL/DASH labels in the top-left HUD. The crystal-asteroid set and ship model are decent, but the flat lavender floor has little of the neon glow or juice the brief asks for.
Claude Opus 5.5 one-shot build of Neoncity — GoldieBench AI benchmark screenshot▶ LIVE
Neoncity
Game
Dense neon canyon with rain, a glowing arch, lit windows, a detailed blue car with boost glow, and a cohesive hull/boost/score/minimap HUD. It plays and looks the part. The buildings are flat-coloured window grids with little bloom or reflection, so it sits just under the 9.0 best.
Claude Opus 5.5 one-shot build of Neonracer — GoldieBench AI benchmark screenshot▶ LIVE
Neonracer
Game
Strong synthwave look (neon grid, window-lit towers, palms, cyan/magenta road lines) with a coherent HUD. The car is a blocky box assembly, and the vapor trails show up as a few white streak slabs rather than a lush particle effect.
Claude Opus 5.5 one-shot build of Nordiccrypt — GoldieBench AI benchmark screenshot▶ LIVE
Nordiccrypt
Game
Warm torch-lit brick corridors with bones, barrels, a rune counter, a minimap and a cohesive Nordic HUD make it a proper first-person crawler. The held torch flame is a solid white cone, the axe-sword and hands are crude flat blocks, and no draugr is in view, well short of the field's 9.5 best.
Claude Opus 5.5 one-shot build of Outrun — GoldieBench AI benchmark screenshot▶ LIVE
Outrun
Game
Strong synthwave palette: striped sun, magenta grid, palms, SUNSET 1986 billboards, a modelled red car, traffic/hostiles and a tidy HUD. It uses a real 3D road rather than pseudo-3D, and the dim km/h label and chunky boxy cars keep it short of the top.
Claude Opus 5.5 one-shot build of Pool — GoldieBench AI benchmark screenshot▶ LIVE
Pool
Game
Physics, pockets, scratch logic and a minimap are real, but the brief is reframed as a 'Rogue Break' combat game with hull, kills and hostiles. The mid-play frame is mostly checkered floor, with the cue ball respawning and the table barely visible, so a player can't read the game.
Claude Opus 5.5 one-shot build of Raycaster — GoldieBench AI benchmark screenshot▶ LIVE
Raycaster
Game
Convincing Wolfenstein mood: textured stone corridors, red eagle banners, moss, torches, a cobbled floor, a guard, a treasure chalice and a first-person gun, with a cohesive HUD and minimap. It is a full three.js scene rather than a true raycaster, and the gun and hand are blocky boxes.
Claude Opus 5.5 one-shot build of Rpg — GoldieBench AI benchmark screenshot▶ LIVE
Rpg
Game
EYEBALL GATE: the circular minimap covers the GOLD/KILLS/FOES/WAVE panel, so the HUD is not one cohesive layer. Heavy white bloom washes out the combat zone and a pillar hides the player, even though the hotbar, low-poly world and damage numbers are solid.
Claude Opus 5.5 one-shot build of Matrixrain — GoldieBench AI benchmark screenshot▶ LIVE
Matrixrain
Other
Dense, authentic katakana rain with depth-varied glyphs, glow, themes, a shockwave, and a type-your-words feature. The captured frame is paused at 25 fps, and rain glyphs bleed through the PAUSED banner text.
Claude Opus 5.5 one-shot build of Mlx Speedtest — GoldieBench AI benchmark screenshot▶ LIVE
Mlx Speedtest
Other
EYEBALL GATE: the chip labels (M1 Pro, M1 Max, M2 Ultra, M3 Max, M4 Pro/Max) are half-hidden under their 3D discs. The gauge also shows 7.4 tok/s while the Generation tile shows '— tok/s'. The live-GFLOPS probe, the leaderboard and the orbiting glow are nice ideas, but the 3D bars are flat unlabeled pucks.
Claude Opus 5.5 one-shot build of Neonsnake — GoldieBench AI benchmark screenshot▶ LIVE
Neonsnake
Other
Strong synthwave presentation: a tilted neon 3D grid arena, glowing corner pylons and a clean score/best HUD. The frame shows a paused board with a tiny 4-segment snake. The known bug where body segments snap cell-to-cell while only the head glides makes play choppy.
Claude Opus 5.5 one-shot build of Landing — GoldieBench AI benchmark screenshot▶ LIVE
Landing
Page
Polished dark SaaS page with sticky nav, logo marquee, an interactive 3D glass orb and good feature cards and copy. The fixed orb and its ring cut across the headline and the 'Fable&Co' logo, which clutters the first screen.
Claude Opus 5.5 one-shot build of Webos — GoldieBench AI benchmark screenshot▶ LIVE
Webos 🥉
Page
Polished NovaOS desktop: working Paint, Notes with a sidebar and autosave, a Terminal with neofetch/ls, a menu bar with a live clock and CPU, a side launcher and a dock with running dots, all in one cohesive macOS-like style. Very strong, but not clearly above the field's 9.0 best.
Claude Opus 5.5 one-shot build of Blackhole — GoldieBench AI benchmark screenshot▶ LIVE
Blackhole
Sim
Striking real ray-marched Schwarzschild lensing: the Einstein ring bends over the top, the photon ring is thin and bright, the disk is Doppler-beamed and the streaked starfield looks good; controls are clean. Right up with the field's best, though the disk's banded ripple texture looks slightly synthetic.
Claude Opus 5.5 one-shot build of Boids — GoldieBench AI benchmark screenshot▶ LIVE
Boids
Sim
Real 3D flock of 600 with live separation/alignment/cohesion sliders, predator, attractors and a clean HUD. The boids are near-black cones on a dark purple scene, so the flock reads dim and hard to follow.
Claude Opus 5.5 one-shot build of Cloth — GoldieBench AI benchmark screenshot▶ LIVE
Cloth
Sim
Real Verlet cloth (2,116 particles) with a nice plaid texture, drag, shape swap and wind. In the frame the cloth has slid off and lies in a heap beside the sphere instead of draping over it, and the washed-out lavender floor takes up most of the screen.
Claude Opus 5.5 one-shot build of Fluid — GoldieBench AI benchmark screenshot▶ LIVE
Fluid
Sim
Real GPU Navier-Stokes with vorticity: vivid curling dye plumes and a dense advected particle layer read as a proper swirling fluid, and the control pills are tidy. The stats line still says a stale 'starting…', and the look is a little busy next to the field's 9.0 best.
Claude Opus 5.5 one-shot build of Fractal — GoldieBench AI benchmark screenshot▶ LIVE
Fractal
Sim
Rich Mandelbrot deep zoom with an auto-tour, palette cycling, a live Julia-at-cursor preview and a tidy coordinate HUD. A hard straight-edged black band cuts across the right third of the frame, which looks like an interior/render artifact.
Claude Opus 5.5 one-shot build of Galaxy — GoldieBench AI benchmark screenshot▶ LIVE
Galaxy
Sim
90k-star spiral with a glowing core, dust lanes, a mouse vortex, palettes and a clean HUD. It looks gorgeous overall. Visible vertical streak artifacts at the core (particles pulled into columns) mar the centrepiece.
Claude Opus 5.5 one-shot build of Orbit — GoldieBench AI benchmark screenshot▶ LIVE
Orbit
Sim
Strong N-body sim: leapfrog integrator, energy-drift readout, 5 scenarios (figure-8, galaxy collision), trails and a click-to-add planet/star, all in a clean cohesive HUD over a glowing polar grid. The scene is a little sparse and dim at this zoom.
Claude Opus 5.5 one-shot build of Particleforge — GoldieBench AI benchmark screenshot▶ LIVE
Particleforge
Sim
38k-particle GPU galaxy with gravity wells, repel, swirl, detonate and 4 modes, shown in a tidy stats panel and mode pills. The frame is sparse and almost single-hue purple even though the palette reads EMBER, so it lacks the wow density of the top entries.
Claude Opus 5.5 one-shot build of Pathtracer — GoldieBench AI benchmark screenshot▶ LIVE
Pathtracer
Sim
A genuine progressive path tracer: a Cornell box with color bleeding, Fresnel glass with caustics, a mirror sphere, soft shadows, samples/paths-per-second telemetry and useful controls. At 17 spp it is still grainy, and the subtitle runs faintly into the render.
Claude Opus 5.5 one-shot build of Reactiondiff — GoldieBench AI benchmark screenshot▶ LIVE
Reactiondiff
Sim
A feature-rich Gray-Scott lab (8 presets, palettes, a clickable f/k parameter map, 3D-light and mirror-brush modes, autopilot) with a tidy panel. The 256x144 simulation is upscaled into blurry, soft blobs, and the title and subtitle are crossed by the pattern, so it lacks the crisp detail of the best entries.
Claude Opus 5.5 one-shot build of Solar — GoldieBench AI benchmark screenshot▶ LIVE
Solar
Sim
Accurate live Keplerian orrery driven by JPL J2000 elements: sqrt/true-distance scale toggle, asteroid belt, ringed Saturn, time controls and a real data panel, all in a polished UI. Planets are tiny at this zoom and the view is a fairly standard top-down orrery.
Claude Opus 5.5 one-shot build of Wormhole — GoldieBench AI benchmark screenshot▶ LIVE
Wormhole
Sim
Striking glowing lattice tunnel with real depth, sector themes, velocity/distance HUD, warp and barrel roll, and it is clean and on-brief. The bloom is heavy enough to blow out the outer frame, and it is just short of the field best.
Claude Opus 5.5 one-shot build of Aurora — GoldieBench AI benchmark screenshot▶ LIVE
Aurora
Visual
Lovely low-poly valley: layered shader aurora curtains, snowy peaks, a glowing cabin and a mirror lake reflection, plus palette and substorm controls. The foreground snow is a flat, overexposed cyan band that eats the bottom third of the frame.
Claude Opus 5.5 one-shot build of Fireworks — GoldieBench AI benchmark screenshot▶ LIVE
Fireworks
Visual
Polished harbour show with a skyline, Ferris wheel, moon, 10 shell types (ring, heart, willow) and a live spark counter. The harbour water is washed-out pale blue instead of dark night water, and the buildings are flat grey slabs.
Claude Opus 5.5 one-shot build of Lavalamp — GoldieBench AI benchmark screenshot▶ LIVE
Lavalamp
Visual
Well-crafted lamp body with metallic cap and base, a glow and a palette HUD. The wax itself reads poorly: a single bubbly blob with dark speckled shading stuck at the top and a pool at the bottom, not the smooth slow-morphing lava the brief is about.
Claude Opus 5.5 one-shot build of Matrix — GoldieBench AI benchmark screenshot▶ LIVE
Matrix
Visual
Dense, authentic green katakana rain with real depth layering, glow and bright lead glyphs, plus parallax, fly, ripple and colour controls. The capture shows the rain paused, and the title and stats panels sit over the rain.
Claude Opus 5.5 one-shot build of Plasma — GoldieBench AI benchmark screenshot▶ LIVE
Plasma
Visual
Smooth, hypnotic GPU plasma with 8 palette swatches, speed/scale/warp sliders and a visible click ripple, all in tidy minimal UI. It is on-brief and polished but not quite the field-best wow.
Claude Opus 5.5 one-shot build of Synthwave — GoldieBench AI benchmark screenshot▶ LIVE
Synthwave
Visual
Nails the look: a striped setting sun, neon wireframe mountains, palm-lined highway, a car with neon tail-lights, a chrome title and synth music on M. It is close to the field best but not clearly above it. The car is a dark low-detail silhouette.
Claude Opus 5.5 one-shot build of Terrain — GoldieBench AI benchmark screenshot▶ LIVE
Terrain
Visual
Infinite chunked ridged-fBm terrain with a minimap, day-time cycle, autopilot and stats HUD works. The render is washed out, with milky beige-grey peaks, heavy haze, blurry billboard clouds and sparse cone trees at 20 fps, and the title is barely legible.
Claude Opus 5.5 one-shot build of Voxel — GoldieBench AI benchmark screenshot▶ LIVE
Voxel
Visual
Bright, varied voxel island (15k blocks) with terraced grass, beaches, water, pastel trees, seeded regen and a day cycle. Pleasant and on-brief. Leaf blocks carry a noisy black-speckle texture and the lighting is flat midday with no fog or shadow depth, so it's below the 9.0 best.
Claude Opus 5.5 one-shot build of Waves — GoldieBench AI benchmark screenshot▶ LIVE
Waves
Visual
Gerstner ocean with a believable choppy surface, specular sunset glints, a bobbing buoy and sailboat, gulls, and a live sea-state readout. The sliders and presets panel is well built. Wave crests lack foam and the far field flattens into a painted look.
every demo, in a grid · click any one to play

Compare Claude Opus 5.5 against every other model

Every head-to-head featuring Claude Opus 5.5. Verdicts shown for scored pairs.

Claude Opus 5.5 vs Fusion
Fusion leads 41–5
Claude Opus 5.5 vs Claude Opus 5
Claude Opus 5 leads 43–5
Claude Opus 5.5 vs Hermes MoA
Hermes MoA leads 32–13
Claude Opus 5.5 vs GPT-5.6 Sol
GPT-5.6 Sol leads 44–4
Claude Opus 5.5 vs Claude Fable 5
Claude Fable 5 leads 27–18
Claude Opus 5.5 vs Qwen 3.8
Qwen 3.8 leads 34–10
Claude Opus 5.5 vs Grok
Grok leads 24–17
Claude Opus 5.5 vs MiniMax M3
MiniMax M3 leads 28–17
Claude Opus 5.5 vs Fugu Ultra
Fugu Ultra leads 28–13
Claude Opus 5.5 vs Kimi K3
Kimi K3 leads 38–11
Claude Opus 5.5 vs GLM-5.2
Claude Opus 5.5 leads 22–21
Claude Opus 5.5 vs Fugu Mini
Claude Opus 5.5 leads 18–17
Claude Opus 5.5 vs Muse Spark 1.2
Muse Spark 1.2 leads 30–17
Claude Opus 5.5 vs Opus 4.8
Claude Opus 5.5 leads 26–20
Claude Opus 5.5 vs Kimi K2.7
Claude Opus 5.5 leads 16–7
Claude Opus 5.5 vs Grok 4.7
Grok 4.7 leads 12–8
Claude Opus 5.5 vs Qwable 5 27B Coder
Claude Opus 5.5 leads 23–14
Claude Opus 5.5 vs Gemini 3.6 Flash
Tied 23–23
Claude Opus 5.5 vs Claude Sonnet 5
Claude Opus 5.5 leads 24–23
Claude Opus 5.5 vs Qwen 3.7
Claude Opus 5.5 leads 35–11
Claude Opus 5.5 vs Fugu Ultra 1.1
Fugu Ultra 1.1 leads 12–11
Claude Opus 5.5 vs MiMo-V2.6 Pro
MiMo-V2.6 Pro leads 29–20
Claude Opus 5.5 vs Inkling
Claude Opus 5.5 leads 42–7
Claude Opus 5.5 vs Grok 4.6
Claude Opus 5.5 leads 13–7
Claude Opus 5.5 vs Agents-A1
Claude Opus 5.5 leads 37–8
Claude Opus 5.5 vs Gemma 4 12B · MLX
Claude Opus 5.5 leads 38–2
Claude Opus 5.5 vs Laguna XS 2.1
Claude Opus 5.5 leads 42–0
Claude Opus 5.5 vs Qwythos 9B
Claude Opus 5.5 leads 40–2
Claude Opus 5.5 vs LongCat-2.0
LongCat-2.0 leads 3–0
Claude Opus 5.5 vs Hy3
Claude Opus 5.5 leads 6–1
Claude Opus 5.5 vs Gemma-4 12B Coder
Claude Opus 5.5 leads 5–0
Claude Opus 5.5 vs DeepSeek V4 Flash
50 shared tasks · unscored
Claude Opus 5.5 vs DeepSeek V4 Pro
50 shared tasks · unscored
Claude Opus 5.5 vs Kimi K2.7 · Fast
47 shared tasks · unscored
Claude Opus 5.5 vs Kimi K2.7 · No-Think
47 shared tasks · unscored
Claude Opus 5.5 vs Kimi K2.7 · Quality
47 shared tasks · unscored
Claude Opus 5.5 vs Ornith 1.0
42 shared tasks · unscored
Claude Opus 5.5 vs Claude Mythos 5
Reference-only
Claude Opus 5.5 vs Kilo Code
Reference-only

See all 66 comparisons across every model →

Quick pill index

Direct comparisons against every other scored model on the bench:

Claude Opus 5.5 vs Fusion Claude Opus 5.5 vs Claude Opus 5 Claude Opus 5.5 vs Hermes MoA Claude Opus 5.5 vs GPT-5.6 Sol Claude Opus 5.5 vs Claude Fable 5 Claude Opus 5.5 vs Qwen 3.8 Claude Opus 5.5 vs Grok Claude Opus 5.5 vs MiniMax M3 Claude Opus 5.5 vs Fugu Ultra Claude Opus 5.5 vs Kimi K3 Claude Opus 5.5 vs GLM-5.2 Claude Opus 5.5 vs Fugu Mini Claude Opus 5.5 vs Muse Spark 1.2 Claude Opus 5.5 vs Opus 4.8 Claude Opus 5.5 vs Kimi K2.7 Claude Opus 5.5 vs Grok 4.7 Claude Opus 5.5 vs Qwable 5 27B Coder Claude Opus 5.5 vs Gemini 3.6 Flash Claude Opus 5.5 vs Claude Sonnet 5 Claude Opus 5.5 vs Qwen 3.7 Claude Opus 5.5 vs Fugu Ultra 1.1 Claude Opus 5.5 vs MiMo-V2.6 Pro Claude Opus 5.5 vs Inkling Claude Opus 5.5 vs Grok 4.6 Claude Opus 5.5 vs Agents-A1 Claude Opus 5.5 vs Gemma 4 12B · MLX Claude Opus 5.5 vs Laguna XS 2.1 Claude Opus 5.5 vs Qwythos 9B Claude Opus 5.5 vs LongCat-2.0 Claude Opus 5.5 vs Hy3 Claude Opus 5.5 vs Gemma-4 12B Coder

Read more on agentos.guide:

Claude Opus 5.5 — frequently asked

What is Claude Opus 5.5?

Claude Opus 5.5 is Anthropic's AI model — Anthropic's Opus 5.5 — benched on all 50 one-shot builds, every game playtested. It has a 1M tokens context window and was released 2026-09.

How good is Claude Opus 5.5 at coding and one-shot builds?

On the GoldieBench one-shot build benchmark it averages 7.57/10 across 50 scored tasks, with 0 gold, 0 silver and 1 bronze medals.

How much does Claude Opus 5.5 cost?

$4 / $20 per M. Anthropic's Opus 5.5 — 1M-token context, listed at $4 input / $20 output per million tokens. Benched through a Claude subscription; game tasks use our skill-infused AAA build prompts.

Where can I see Claude Opus 5.5 demos?

Every one-shot build is live and playable on this page and on the GoldieBench compare matrix — same prompt as every other model, no retries.

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