Real head-to-head · same prompt, one shot

Fusion vs Hy3

Multi-model panel — Fable 5 + GPT-5.5, ensembled. Beats Fable 5 at half the price. vs Tencent's open-weights coder — Apache-2.0, cheap, beats GLM-5.1 on frontend in Tencent's blind eval.

Head-to-head verdict: Fusion wins 7–0.

Fusion · contextVaries (per-panel)
Hy3 · context262K tokens
Fusion · priceOpenRouter Fusion API pricing
Hy3 · price$0.14 / 1M input · $0.58 / 1M output
Fusion · vendorOpenRouter
Hy3 · vendorTencent Hunyuan

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 Fusion and Hy3, side by side, on 7 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.

Fusion · Dispatched from Agent OS for research-heavy prompts where ensemble accuracy outweighs single-model speed.

Hy3 · Wired into the Agent OS as the 'Hy3 Coder' tab (chat + live preview + workspace) via OpenRouter. Bench built one-shot on the same prompts as the field; weak builds iterated by Hy3 itself (the model fixes its own builds).

Side-by-side on 47 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 ↓
Fusion
Hy3
Game
🥈Fusion on Doom
Hy3 on Doom
🥇Fusion on Dragonrealm
Hy3 on Dragonrealm
Game
🥇Fusion on Flightsim
🥈Hy3 on Flightsim
Game
🥇Fusion on Gtadrive
Hy3 on Gtadrive
Game
🥇Fusion on Gtafoot
Hy3 on Gtafoot
Game
🥇Fusion on Parachute
Hy3 on Parachute
Page
🥈Fusion on Aipbpromo
Hy3 on Aipbpromo
Game
🥈Fusion on Arcade
— not attempted —
Game
🥇Fusion on Crypt
— not attempted —
Game
🥇Fusion on Dogfight
— not attempted —
🥇Fusion on Dragonflight
— not attempted —
Game
🥇Fusion on Game
— not attempted —
🥇Fusion on Neonblaster
— not attempted —
Game
🥈Fusion on Neoncity
— not attempted —
Game
🥇Fusion on Neonracer
— not attempted —
🥇Fusion on Nordiccrypt
— not attempted —
Game
Fusion on Outrun
— not attempted —
Game
🥉Fusion on Pool
— not attempted —
Game
🥇Fusion on Racing
— not attempted —
Game
🥇Fusion on Raycaster
— not attempted —
Game
🥉Fusion on Rpg
— not attempted —
Game
🥇Fusion on Skyrim
— not attempted —
🥇Fusion on Twilightvale
— not attempted —
Game
🥇Fusion on Voxelcraft
— not attempted —

Where Fusion beat Hy3

The tasks where I gave Fusion a higher 0–10 score on the same prompt — with the actual commentary from my source guides.

Doom Game
Fusion 8.5 · Hy3 5.5 (+3.0)

What I saw: Doom-style raycaster shooter: sprite enemies, gun with muzzle flash, ammo + health HUD. WASD + mouse-look + click to fire. 20KB of game logic.

Fusion 9.0 · Hy3 7.2 (+1.8) · winner · Dragon Realm

What I saw: The Dragon Realm — Skyrim-style frozen open world with full HUD (score/vitality/stamina), snowy mountains, low-poly pine forest, a flying dragon. WASD + mouse-look. Tied with GLM's deep build at the top of the task.

Gtafoot Game
Fusion 8.8 · Hy3 7.2 (+1.6) · showcase · game-director

What I saw: SHOWCASE BUILD (threejs-game-director): articulated humanoid w/ walk cycle + weapon poses, 110 instanced buildings w/ lit windows, 16 neon blade signs, wet-road reflections, cops+peds AI, cohesive GTA HUD (cash/minimap/stars/weapon wheel), 71fps. Eyeball-gate passed.

Parachute Game
Fusion 8.8 · Hy3 7.2 (+1.6) · showcase · game-director

What I saw: SHOWCASE BUILD (threejs-game-director): cargo-bay interior + jump light, articulated skydiver w/ 7 pose sets, 9-cell ram-air canopy w/ lines, 11.5k instanced trees + carved river, ring-target landing scoring, analog altimeter HUD, auto-demo lands inner ring. Eyeball-gate passed.

Gtadrive Game
Fusion 9.0 · Hy3 7.4 (+1.6) · showcase · game-director

What I saw: SHOWCASE BUILD (threejs-game-director): beveled car bodies w/ glass + spinning wheels, sunset sky + PMREM paint reflections, 15-car lane AI + red lights + overtakes, cop pursuit, drift smoke + skids, arc speedometer + minimap HUD, 77 draw calls 71fps. Eyeball-gate passed.

Strengths & weaknesses I logged

Fusion

Strengths

  • Premium Fusion panel scored 69.0% on DRACO deep-research benchmark — beats solo Fable 5 by +3.7 points
  • Budget panel ties Fable 5 at ~64.7% for roughly half the cost
  • Vendor-agnostic — model panel can swap as new frontier releases land

Trade-offs

  • Ensemble latency higher than any single model (panel calls run in parallel but the slowest still gates the response)
  • No per-task goldiebench scoring yet — bench rank pending

Hy3

Strengths

  • Apache-2.0 open weights — self-host free, no lock-in
  • Tencent's 270-expert blind eval: 2.67/4 vs GLM-5.1's 2.51, strongest on frontend / data / CI-CD
  • Hallucination rate cut 12.5% → 5.4%; stable tool-calls across scaffoldings (<4% SWE-Bench variance)

Trade-offs

  • Slow upstream on OpenRouter (30-90s per build) — fine for one-shots, sluggish for tight loops
  • One-shot game builds can under-render (flat raycaster walls, unlit 3D) without an iterate pass

Pricing & context — the spec sheet

Spec Fusion Hy3
VendorOpenRouterTencent Hunyuan
Context windowVaries — depends on which panel models are dispatched262,144-token context window. Open weights (Apache-2.0) on HuggingFace / ModelScope / GitHub; benched here via OpenRouter.
PriceOpenRouter Fusion API pricing$0.14 / 1M input · $0.58 / 1M output
Pricing detailOpenRouter's Fusion API dispatches a single prompt to multiple frontier models and ensembles the answers. Premium panel: Fable 5 + GPT-5.5. Budget panel: cheaper open-weights models. Roughly half the per-token cost of a Fable 5 solo call.Tencent Hunyuan 3 — open-weights under Apache-2.0, so free to self-host. On OpenRouter it is one of the cheapest capable coders: ~$0.14/M in, $0.58/M out (1 RMB / 4 RMB). Upstream can be slow (30-90s to first token), but per-token cost is negligible.
Release2026-06-142026-07-06
Bench coverage47/47 scored · avg 8.59/107/7 scored · avg 7.13/10

The verdict — which should you pick?

Across 7 scored shared tasks, Fusion averaged 8.61/10, beating Hy3's 7.13/10 by 1.49 points. Pick Fusion 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 Fusion and Hy3 both into the Agent Operating System and dispatch each from the kanban by task type — deep-research workflows where panel consensus beats single-model answers → Fusion, cost-sensitive coding + frontend design where open weights matter → Hy3. That's the same setup I run for the 3,600+ founders inside the AI Profit Boardroom.

FAQ — Fusion vs Hy3

Which is better, Fusion or Hy3?

On Goldie Bench, Fusion averages 8.61/10 across the shared tasks, with 24 gold, 10 silver, 6 bronze overall. Hy3 averages 7.13/10, with 0 gold, 1 silver, 0 bronze. Fusion wins the head-to-head 7–0.

How much does Fusion cost vs Hy3?

Fusion: OpenRouter's Fusion API dispatches a single prompt to multiple frontier models and ensembles the answers. Premium panel: Fable 5 + GPT-5.5. Budget panel: cheaper open-weights models. Roughly half the per-token cost of a Fable 5 solo call. Hy3: Tencent Hunyuan 3 — open-weights under Apache-2.0, so free to self-host. On OpenRouter it is one of the cheapest capable coders: ~$0.14/M in, $0.58/M out (1 RMB / 4 RMB). Upstream can be slow (30-90s to first token), but per-token cost is negligible.

What's the context window for Fusion vs Hy3?

Fusion has a Varies — depends on which panel models are dispatched context window. Hy3 has a 262,144-token context window. Open weights (Apache-2.0) on HuggingFace / ModelScope / GitHub; benched here via OpenRouter. context window.

When should I pick Fusion over Hy3?

Pick Fusion for: Deep-research workflows where panel consensus beats single-model answers; Cost-sensitive operators who want Fable-5-class output at ~half the bill; Production agents that benefit from vendor-redundancy on every call. The trade-off is the weaknesses we logged on the bench: Ensemble latency higher than any single model (panel calls run in parallel but the slowest still gates the response); No per-task goldiebench scoring yet — bench rank pending.

When should I pick Hy3 over Fusion?

Pick Hy3 for: Cost-sensitive coding + frontend design where open weights matter; Self-hosters who want an Apache-2.0 model they fully own; Anyone wiring a cheap capable coder into a live build panel (Agent OS Hy3 Coder tab). The trade-off is the weaknesses we logged on the bench: Slow upstream on OpenRouter (30-90s per build) — fine for one-shots, sluggish for tight loops; One-shot game builds can under-render (flat raycaster walls, unlit 3D) without an iterate pass.

How does Goldie Bench score Fusion vs Hy3?

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.

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 3,600+ founders shipping with it every day all live inside the AI Profit Boardroom.

3,600+founders
258documented wins
38countries
$59/momonthly