Qwen 3.8
Alibaba's 2.4T flagship — benched through Qoder.
What is Qwen 3.8?
Qwen 3.8 is the Alibaba frontier model with a Served through Alibaba's Qoder agent platform; the 3.8-Max preview has no standalone public context window yet. context window, released 2026-07. Tagline: Alibaba's 2.4T flagship — benched through Qoder.. Official source: qoder.com.
Pricing detail. Qwen3.8-Max-Preview is Alibaba's ~2.4T-parameter flagship, positioned just behind Claude Fable 5. It is NOT on OpenRouter or a public API yet — the only access today is inside Qoder (Alibaba's agentic coding platform, free 2-week Pro trial). Benched here via the Qoder CLI on model `Qwen3.8-Max-Preview`, one-shot.
How I use it inside the Agent OS. Benched on GoldieBench via the Qoder CLI (`qoder-qwen`, model Qwen3.8-Max-Preview) — the only door while it has no public API. Non-game tasks are one-shot like the rest of the field. GAME tasks run in Qoder's real AGENT mode: skill-infused build, then up to 2 QA fix rounds where a vision judge + live console errors are fed back and Qwen 3.8 edits its own file (it took crypt from a black-screen 3.0 to a torch-lit 7.8). Scored on a mid-play frame by the same Opus judge as everyone else.
What I built with Qwen 3.8
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 Qwen 3.8 shipped on the bench: 45 one-shot demos across Served through Alibaba's Qoder agent platform; the 3.8-Max preview has no standalone public context window yet. of context. Of those, 45 are scored against the field with my honest 0–10 from the source guides at agentos.guide.
Strengths
- Skyrim-style open worlds — the Dragon Realm build rendered a lit snowfield, first-person sword and working roaming enemies (7.8)
- Held up across game genres early — voxel sandbox and Doom raycaster both came out shippable
- Runs as a real agentic coder inside Qoder (writes + iterates on files), not just a chat model
Trade-offs
- Torch-lit dungeon (crypt) came out generic (6.3); one open-world RPG one-shot black-screened (twilightvale 2.5) — classic three.js r128 API drift
- Preview is Qoder / Token-Plan only — no OpenRouter or public API, so it can't be routed into an app the way the OpenRouter models can
Best for
- One-shot 3D game and world prototypes where atmosphere matters
- Anyone already in the Qoder IDE/CLI wanting a near-frontier model free on the Pro trial
- A cheaper stand-in for Fable 5 on creative-visual builds
Every benchmark — Qwen 3.8's full scorecard
All 45 scored tasks, best first — the judge's 0–10 on the same rubric as the whole field. Click any bar for that task's cross-model page, or open this scorecard in the interactive graphs. Full editorial breakdown with judge quotes and sourced outside research: the Qwen 3.8 deep dive →.
Every demo by Qwen 3.8
45 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.
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVECompare Qwen 3.8 against every other model
Every head-to-head featuring Qwen 3.8. Verdicts shown for scored pairs.
See all 66 comparisons across every model →
Quick pill index
Direct comparisons against every other scored model on the bench:
Qwen 3.8 vs Fusion Qwen 3.8 vs Claude Opus 5 Qwen 3.8 vs Hermes MoA Qwen 3.8 vs GPT-5.6 Sol Qwen 3.8 vs Claude Fable 5 Qwen 3.8 vs Grok Qwen 3.8 vs MiniMax M3 Qwen 3.8 vs Fugu Ultra Qwen 3.8 vs Kimi K3 Qwen 3.8 vs GLM-5.2 Qwen 3.8 vs Fugu Mini Qwen 3.8 vs Claude Opus 5.5 Qwen 3.8 vs Muse Spark 1.2 Qwen 3.8 vs Opus 4.8 Qwen 3.8 vs Kimi K2.7 Qwen 3.8 vs Grok 4.7 Qwen 3.8 vs Qwable 5 27B Coder Qwen 3.8 vs Gemini 3.6 Flash Qwen 3.8 vs Claude Sonnet 5 Qwen 3.8 vs Qwen 3.7 Qwen 3.8 vs Fugu Ultra 1.1 Qwen 3.8 vs MiMo-V2.6 Pro Qwen 3.8 vs Inkling Qwen 3.8 vs Grok 4.6 Qwen 3.8 vs Agents-A1 Qwen 3.8 vs Gemma 4 12B · MLX Qwen 3.8 vs Laguna XS 2.1 Qwen 3.8 vs Qwythos 9B Qwen 3.8 vs LongCat-2.0 Qwen 3.8 vs Hy3 Qwen 3.8 vs Gemma-4 12B CoderRead more on agentos.guide:
Qwen 3.8 — frequently asked
What is Qwen 3.8?
Qwen 3.8 is Alibaba's AI model — Alibaba's 2.4T flagship — benched through Qoder. It has a Qoder-hosted context window and was released 2026-07.
How good is Qwen 3.8 at coding and one-shot builds?
On the GoldieBench one-shot build benchmark it averages 8.10/10 across 45 scored tasks, with 8 gold, 6 silver and 7 bronze medals.
How much does Qwen 3.8 cost?
Qoder plan. Qwen3.8-Max-Preview is Alibaba's ~2.4T-parameter flagship, positioned just behind Claude Fable 5. It is NOT on OpenRouter or a public API yet — the only access today is inside Qoder (Alibaba's agentic coding platform, fr
Where can I see Qwen 3.8 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.
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 3,400+ founders shipping with it every day all live inside the AI Profit Boardroom.