Alibaba's Qwen team officially released Qwen3.8-Max on August 3 — and for the first time, they committed to open-sourcing a Max-class model's weights: 2.4T total parameters, 95B active, large enough to cross the "largest open-weight LLM" line, with weights promised for Hugging Face and ModelScope "next week".

Not just another big model: an architectural swap

Compared to the Qwen3.5-era Gated DeltaNet + sparse MoE hybrid, Qwen3.8 changes four things at the foundation. Flash-Next serves as this generation's architectural preview: 125B main model + 51B N-gram embeddings, with 6B parameters activated per token. The changes fall on four layers.

  • Attention: Gated DeltaNet (GDN) continues to compress history; the newly added Qwen Sparse Attention (QSA) uses a compressed lightweight indexer to pick salient context at micro-block granularity, cutting the cost of attention on long sequences.
  • Residual stream: Gated Residual (GR) widens the residual stream into 4 branches and controls reads/writes through a dynamic gate, stabilizing cross-layer information flow and training stability.
  • Embedding: N-gram Embedding uses local context to look up tables that scale capacity at very little extra compute; the embedding table can be offloaded to host memory and overlapped with model computation via asynchronous prefetching.
  • Optimizer: the whole stack moves to the Muon optimizer, re-tuned around orthogonalization accuracy, the division of labor between Muon and AdamW, and the splitting of fused parameters; scaling laws are also re-fit for the new architecture.

In official framing, the position of this new architecture is unambiguous: Qwen3.8-Flash-Next plays the same role Qwen3-Next once played for Qwen3.5 — ship the architectural change first so the community can stress-test it, then stack the full Qwen4 family on top.

Benchmarks: head-on against GPT-5.6 Sol, Fable 5, Opus 4.8

The official comparison table covers 38 benchmarks. Highlights: Terminal Bench 2.1 — Qwen3.8-Max 86.6, close to GPT-5.6 Sol's 88.8, beating Opus 4.8 and Fable 5 at 84.6; PaperBench 93.0, beating GPT-5.6 Sol (90.5), Fable 5 (88.8), Opus 4.8 (80.3); AndroidBench 75.1, still behind Fable 5's 84.5 but ahead of GPT-5.6 Sol's 74.0.

On the vision side the gap is more dramatic: BabyVision 82.0 / 91.3 (without / with Code Interpreter), leaving Opus 4.8's 28.4 / 81.2 far behind; HLE-VL (w/ Tools) 52.2, ahead of GPT-5.6 Sol's 51.2; ZeroBench Pass@5 24.0 / 49.0, also the highest in the field. Across multimodal document and video benchmarks — OmniDocBench 1.5, Video MME (w/ Sub.), MLVU (M-Avg), LVBench — Qwen3.8-Max takes first place on multiple items.

But the team is upfront about the gaps: HLE 43.6 trails Fable 5's 53.3 and GPT-5.6 Sol's 47.2; OSWorld 2.0 binary score 19.4 is below Fable 5's 66.1; Toolathlon Verified 72.5 is also below Fable 5's 77.9. In short, on coding and vision Qwen3.8-Max matches or surpasses the closed frontier; on general reasoning and ultra-long-horizon planning it still trails the top Claude and GPT variants.

Long-context: 1M is default, agent tools already ship

A 1M context window is standard across the Qwen3.8 line. The official best-practice guide recommends 262,144 tokens for internal reasoning output and 131,072 tokens for the final response within the 1M budget, so long tool-call chains can keep a complete reasoning trace.

Qwen3.8 also supports reasoning_effort (xhigh / medium / low) for explicit thinking-depth control and enables preserve_thinking by default, so the chain of thought accumulates across turns — exactly what agent scenarios need ("don't reset reasoning every turn"). MRCR v2 256K (8-needle) reaches 92.9, LongBench v2 66.3 — essentially neck-and-neck with GPT-5.6 Sol's 93.8 / 67.1.

On the API side, Qwen3.8 serves OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages simultaneously, so Claude Code, Codex, Qoder CLI, Qwen Code, and OpenClaw can drop in with a base_url swap.

Three long-horizon demos: 16 days of autonomous coding

The most uncomfortable part of the launch blog is the trio of "long-horizon autonomy" demos.

  • A self-evolving engineering harness, 10+ days. Asked to create the oh-my-cli project from scratch, Qwen3.8-Max ran autonomously for 16 consecutive days, accumulating 265 commits, 127 PRs, 151 issues — the GitHub repository is fully public.
  • Reproduce a paper, then improve it. Starting from a single arXiv paper, the model worked continuously for ~5 days — about 125 hours, ~7,600 lines of code, 33 rounds of GPU training, 1,100+ actions — first reproducing the paper's 6 main findings, then running 4 rounds of self-proposed improvements (18 ideas in total) and beating the paper's method by +2.71 points on AIME24.
  • Beat 526 human teams in 24 hours. On the Tianchi WWW2025 Multimodal Dialogue Intent Recognition Challenge, with 45 submissions the model climbed from 0.60 to a final 0.853 accuracy, beating 458 of 526 (87%) human teams.

None of these is a single benchmark crown. Together they put the engineering question "can the model carry an open-ended goal on its own for a stretch of time?" on the table.

Work side: covering hundreds of high-value professions

The other piece the team emphasizes is "work" — the messy, multi-step, tool-heavy tasks that drive economic value. The model was stress-tested across hundreds of real professional workflows: surfacing 1,284 relevant clauses across hundreds of contract documents in one pass (a paralegal team's week of collaborative work); producing an 8-screen interactive prototype with zero rounds of human revision (a conventional UI/UX flow takes 3–5 rounds); generating a complete 26-dish menu from 100+ ingredient briefs, holding food cost at 33.8%; reconstructing a 30-story office tower's seismic structural model from a single drawing set, inspectable in browser; turning a 2D rehab assessment form into a 3D interactive demo; parsing ~8,400 possessions per player into ready-to-use tactical profiles.

Qwen3.8-Max also demonstrates an end-to-end ETF rotation quant strategy pipeline: starting from a one-line task description, the model autonomously plans the workflow, builds the data system, runs multi-round greedy iteration, and triggers pruning automatically when it detects design-vs-validation-period metric divergence (a classic overfitting signal). On the breadth side, 6 short descriptions (momentum, value, quality, investment, low-risk, sentiment) are decomposed into 50 research directions, ~330 sub-agents, and ~6,000 backtests, with selected factors achieving excess Sharpe ratios of 0.64–1.48.

Gaps and next steps

The team's own caveats are candid: the benchmark suite covers only 10 categories of alignment failures and cannot cover unknown, rare, or newly emergent failures; gains may not survive intensive production RLHF post-training; the AAR capability gate only rejects regressions on MMLU / GSM8K / IFEval, leaving other capability dimensions unmeasured.

Three follow-up research directions are listed: a rare-risk forecaster (predict what alignment failures will appear in the next model generation from historical data), a research-outcome forecaster (predict whether a long-horizon experiment will work before running it), and stronger control scaffolding (so automated alignment research is more monitorable).

Industry implications

Putting Max-class weights open-source redraws the open-vs-closed frontier: open weights cross the 2T+ total / 95B active threshold for the first time, and the Gated DeltaNet + QSA hybrid pushes long-context compute and memory cost down to a new baseline. For Claude / GPT, the real pressure is not that any single benchmark has been matched, but that the open-source camp now has engineering samples for "long-horizon autonomy + workflow coverage".

For developers, this means 1M default context + three-protocol API + reasoning_effort + preserve_thinking + multi-agent harness support (Claude Code / Codex / Qoder / OpenClaw) out of the box — no more hand-wringing over which base model to put under an agent.

The Qwen team put it bluntly in the citation block: "Qwen3.8-Max is our most capable model to date, and the first open-weight model at Max scale." That's both a product tagline and the actual coordinate of the open-source LLM world in the second half of 2026.

Original article and benchmark tables: Qwen3.8-Max: A New Bar for Coding and Cowork.