Real head-to-head · same prompt, one shot
Claude Opus 5.5 vs Fugu Ultra 1.1
Anthropic's Opus 5.5 — benched on all 50 one-shot builds, every game playtested. vs Sakana's multi-agent orchestrator, v1.1 — routes experts per request.
Head-to-head verdict: Fugu Ultra 1.1 wins 12–11.
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 5.5 and Fugu Ultra 1.1, side by side, on 24 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 5.5 · Benched on all 50 GoldieBench tasks via a Claude subscription: one-shot builds, real renders, pixel-diff playtests on every game, then vision-judged.
Fugu Ultra 1.1 · Benched on GoldieBench via Sakana's Responses API (fugu-ultra-v1.1, xhigh reasoning). Game tasks use the skill-infused threejs-game-director prompt plus a controls+graphics fix loop with an anti-regression clamp, judged on a real mid-play frame by the same Opus judge as the field.
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 5.5
Fugu Ultra 1.1
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Game
Page
Visual
Where Claude Opus 5.5 beat Fugu Ultra 1.1
The tasks where I gave Claude Opus 5.5 a higher 0–10 score on the same prompt — with the actual commentary from my source guides.
Raycaster
Game
Claude Opus 5.5 8.3
·
Fugu Ultra 1.1 2.0
(+6.3)
What I saw: 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.
Neoncity
Game
Claude Opus 5.5 8.4
·
Fugu Ultra 1.1 2.3
(+6.1)
What I saw: 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.
Aurora
Visual
Claude Opus 5.5 8.4
·
Fugu Ultra 1.1 5.5
(+2.9)
What I saw: 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.
Nordiccrypt
Game
Claude Opus 5.5 7.6
·
Fugu Ultra 1.1 5.2
(+2.4)
What I saw: 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 fi…
Pool
Game
Claude Opus 5.5 6.3
·
Fugu Ultra 1.1 4.5
(+1.8)
What I saw: 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.
Where Fugu Ultra 1.1 beat Claude Opus 5.5
The tasks where I gave Fugu Ultra 1.1 a higher 0–10 score on the same prompt — with the actual commentary from my source guides.
Twilightvale
Game
Fugu Ultra 1.1 8.6
·
Claude Opus 5.5 5.5
(+3.1)
· Atmospheric RPG World
What I saw: Gorgeous cohesive twilight scene with detailed hero holding a weapon, visible enemies (creature + humanoid), wooden bridge, lampposts, cottage, river, pickups and a working minimap/HUD with quest and kill tracker. Strong art direction and populated world with combat framing; only…
Rpg
Game
Fugu Ultra 1.1 8.4
·
Claude Opus 5.5 5.5
(+2.9)
· Verdant Relic RPG
What I saw: Polished top-down 3D RPG with visible enemies in aggro rings, active combat ('HIT -13' damage numbers, health at 87), pickups, a shrine objective, and a clean HUD showing inventory/kills/hostiles; strong shippable build, only slightly held back by the inventory system being minim…
Doom
Game
Fugu Ultra 1.1 8.4
·
Claude Opus 5.5 5.8
(+2.6)
· 3D demon shooter
What I saw: Strong atmospheric 3D maze with a visible horned demon enemy, working shotgun, minimap with tracked enemies, and active combat ('CLAWED' hit feedback, HP dropped to 082) — polished HUD and lighting. Falls just shy of the field's best; enemies are more Three.js models than true ra…
Neonblaster
Game
Fugu Ultra 1.1 8.2
·
Claude Opus 5.5 5.8
(+2.4)
What I saw: Polished 3D low-poly arcade shooter with visible enemies, active combat state (score 238, kills 1, health 75, 5 enemies), power-up pickups, crystals/asteroids scenery and a clean neon HUD — clearly functional and juicy; slightly generic ground-based feel rather than a true space …
Parachute
Game
Fugu Ultra 1.1 8.6
·
Claude Opus 5.5 7.6
(+1.0)
· combat parachute drop
What I saw: Strong deployed-chute skydiver over a jungle canopy with a polished HUD (altitude, dist-to-H, score) plus active drone enemies, flare combat, and 'THREAT DOWN' kill feedback — it delivers the full jump/steer/land loop AND working combat, edging past a bland walking sim.
Strengths & weaknesses I logged
Claude Opus 5.5
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)
Fugu Ultra 1.1
Strengths
- Orchestrates 1-3 expert agents per request and synthesises their answers
- Reported SWE-Bench Pro 73.7 — above Opus 4.8 and GPT-5.5 on Sakana's table
- OpenAI- and Anthropic-compatible API — drop-in for Codex and Claude Code
Trade-offs
- Benched as a partial run until the full 50-task batch completes
- Region-locked: unavailable across the EU/EEA/UK/CH — access depends on where you are
Pricing & context — the spec sheet
| Spec | Claude Opus 5.5 | Fugu Ultra 1.1 |
|---|---|---|
| Vendor | Anthropic | Sakana AI |
| Context window | 1,000,000 tokens | 1,000,000-token context window |
| Price | $4 / $20 per M | API · orchestration billed |
| 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. | Sakana's Fugu Ultra v1.1 — a multi-agent system served as a model: an orchestrator routes each request across one to three expert agents and synthesises the answer. Reported (v1.0): SWE-Bench Pro 73.7, LiveCodeBench 93.2, GPQA Diamond 95.5. NOTE: Sakana geo-blocks the EU/EEA/UK/Switzerland pending GDPR compliance — benched from an allowed region. |
| Release | 2026-09 | 2026-07 |
| Bench coverage | 50/50 scored · avg 7.57/10 | 23/24 scored · avg 6.94/10 |
The verdict — which should you pick?
Across 23 scored shared tasks, Claude Opus 5.5 averaged 7.26/10, beating Fugu Ultra 1.1's 6.94/10 by 0.32 points. Pick Claude Opus 5.5 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 5.5 and Fugu Ultra 1.1 both into the Agent Operating System and dispatch each from the kanban by task type — hardest agentic builds → Claude Opus 5.5, hard, high-stakes coding and reasoning where answer quality beats latency → Fugu Ultra 1.1. That's the same setup I run for the 4,000+ founders inside the AI Profit Boardroom.
FAQ — Claude Opus 5.5 vs Fugu Ultra 1.1
Which is better, Claude Opus 5.5 or Fugu Ultra 1.1?
On Goldie Bench, Claude Opus 5.5 averages 7.26/10 across the shared tasks, with 0 gold, 0 silver, 1 bronze overall. Fugu Ultra 1.1 averages 6.94/10, with 0 gold, 1 silver, 1 bronze. Fugu Ultra 1.1 wins the head-to-head 12–11.
How much does Claude Opus 5.5 cost vs Fugu Ultra 1.1?
Claude Opus 5.5: 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. Fugu Ultra 1.1: Sakana's Fugu Ultra v1.1 — a multi-agent system served as a model: an orchestrator routes each request across one to three expert agents and synthesises the answer. Reported (v1.0): SWE-Bench Pro 73.7, LiveCodeBench 93.2, GPQA Diamond 95.5. NOTE: Sakana geo-blocks the EU/EEA/UK/Switzerland pending GDPR compliance — benched from an allowed region.
What's the context window for Claude Opus 5.5 vs Fugu Ultra 1.1?
Claude Opus 5.5 has a 1,000,000 tokens context window. Fugu Ultra 1.1 has a 1,000,000-token context window context window.
When should I pick Claude Opus 5.5 over Fugu Ultra 1.1?
Pick Claude Opus 5.5 for: Hardest agentic builds; Whole-repo reasoning; Frontier one-shots. The trade-off is the weaknesses we logged on the bench: 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).
When should I pick Fugu Ultra 1.1 over Claude Opus 5.5?
Pick Fugu Ultra 1.1 for: Hard, high-stakes coding and reasoning where answer quality beats latency; Agentic workflows in Codex / Claude Code via the drop-in provider config; One-shot builds you want a panel of experts on, not a single model. The trade-off is the weaknesses we logged on the bench: Benched as a partial run until the full 50-task batch completes; Region-locked: unavailable across the EU/EEA/UK/CH — access depends on where you are.
How does Goldie Bench score Claude Opus 5.5 vs Fugu Ultra 1.1?
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 5.5 vs Fusion Fugu Ultra 1.1 vs Fusion Claude Opus 5.5 vs Claude Opus 5 Fugu Ultra 1.1 vs Claude Opus 5 Claude Opus 5.5 vs Hermes MoA Fugu Ultra 1.1 vs Hermes MoA Claude Opus 5.5 vs GPT-5.6 Sol Fugu Ultra 1.1 vs GPT-5.6 SolFull model pages: Claude Opus 5.5 · Fugu Ultra 1.1 · 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