Fugu Ultra v2.0 vs Qwen 3.7 Max

Sakana AI · Global  |  Alibaba · China · Updated June 2026

Quick verdict

Pick Fugu Ultra v2.0 for sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark or claims to outperform flagship models like gpt-6 astra and claude fable 5.1 despite its underlying orchestration pool reportedly excluding both of them. Pick Qwen 3.7 Max for long-horizon agentic coding (swe-bench pro 60.6, terminal-bench 2.0 69.7) or 1m-token long-document and full-codebase analysis. On a tight budget at scale, Qwen 3.7 Max is the value pick.

Fugu Ultra v2.0 (Sakana AI) and Qwen 3.7 Max (Alibaba) are two of the models people most often weigh against each other in 2026. Fugu Ultra v2.0 is sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens. Qwen 3.7 Max is alibaba's agent-first frontier model — a 1M-token context and long-horizon coding at about half the cost of US flagships. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.

Key differences at a glance

Side-by-side specs

SpecFugu Ultra v2.0Qwen 3.7 Max
ProviderSakana AI (Global) Alibaba (China)
ReleasedSeptember 10, 2026 May 20, 2026
Context window1M tokens (~1,500 pages) 1M (~1,500 pages)
Price (in/out)$5/$30 per 1M tokens $2.5/$7.5 per 1M tokens
Open weight?No — API only No — API only
Modalitiestext text, code
SWE-Bench VerifiedNot published Not published
MRCR v2 @ 1MNot published Not published

Who wins what

Sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the DeepSWE coding-repair benchmark

Fugu Ultra v2.0

Sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens — and it is the newer of the two.

Claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them

Fugu Ultra v2.0

Qwen 3.7 Max is comparatively weak here — trails GPT-5.5 and Claude Opus on the hardest one-shot reasoning

1M-token context window

Fugu Ultra v2.0

Fugu Ultra v2.0 lists 1M-token context window among its strengths; Qwen 3.7 Max does not.

Long-horizon agentic coding (SWE-Bench Pro 60.6, Terminal-Bench 2.0 69.7)

Qwen 3.7 Max

Fugu Ultra v2.0 is comparatively weak here — not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that dynamically routes tasks across a pool of other models, so head-to-head benchmark framing against monolithic frontier models should be read skeptically

1M-token long-document and full-codebase analysis

Qwen 3.7 Max

Fugu Ultra v2.0 is comparatively weak here — pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens

MCP tool orchestration and multi-hour autonomous runs

Qwen 3.7 Max

Alibaba's agent-first frontier model — a 1M-token context and long-horizon coding at about half the cost of US flagships — and it runs cheaper at $2.5/$7.5 per 1M tokens.

Lowest cost at scale

Qwen 3.7 Max

At $2.5/$7.5 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.

Which should you pick?

A cost-sensitive startup shipping high volume

Qwen 3.7 Max

At $2.5/$7.5 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.

Anyone whose priority is sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark

Fugu Ultra v2.0

It is specifically built for that.

Anyone whose priority is long-horizon agentic coding (swe-bench pro 60.6, terminal-bench 2.0 69.7)

Qwen 3.7 Max

That is its strongest area.

Fugu Ultra v2.0: where it fits

Sakana AI's flagship multi-agent orchestration model, claiming best-or-joint-best results on 5 of 8 self-reported benchmarks against monolithic frontier models — $5/$30 per million tokens. Released September 10, 2026 by Sakana AI, it is built for sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the DeepSWE coding-repair benchmark, claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them, and 1M-token context window.

Its trade-offs are real: not a single trained model — Sakana describes Fugu as "a Multi-Agent System, Delivered as One Model" that dynamically routes tasks across a pool of other models, so head-to-head benchmark framing against monolithic frontier models should be read skeptically, pricing rises to roughly $10/$45 per million tokens for prompts above 272K tokens, and benchmark comparisons against GPT-6 Astra and Claude Fable 5.1 are Sakana's own self-reported figures, not independently verified head-to-head scores. At $5 in / $30 out per million tokens, it sits in the premium price band.

Qwen 3.7 Max: where it fits

Alibaba's agent-first frontier model — a 1M-token context and long-horizon coding at about half the cost of US flagships. Released May 20, 2026 by Alibaba, it is built for long-horizon agentic coding (SWE-Bench Pro 60.6, Terminal-Bench 2.0 69.7), 1M-token long-document and full-codebase analysis, mCP tool orchestration and multi-hour autonomous runs, and frontier intelligence at roughly half the price of US flagships.

Its trade-offs: text-only — no vision input (the Plus variant adds images), closed-weight, API-only — no self-hosting, trails GPT-5.5 and Claude Opus on the hardest one-shot reasoning, and chinese-jurisdiction data-residency considerations. At $2.5 in / $7.5 out per million tokens, it sits in the mid price band.

The bottom line for this matchup

Fugu Ultra v2.0 and Qwen 3.7 Max overlap enough that the right pick depends on your specific job. Qwen 3.7 Max costs less per token; and each leads in its own area — Fugu Ultra v2.0 for sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark, Qwen 3.7 Max for long-horizon agentic coding (swe-bench pro 60.6, terminal-bench 2.0 69.7). Rather than crowning one, run the same hard task through both once and let the results decide.

Want both Fugu Ultra v2.0 and Qwen 3.7 Max without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.

See pricing

Frequently asked questions

Is Fugu Ultra v2.0 or Qwen 3.7 Max better for coding?

Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Fugu Ultra v2.0 leans toward sakana's own evaluation reports best-or-joint-best results on 5 of 8 benchmarks tested, including a 74.3 on the deepswe coding-repair benchmark while Qwen 3.7 Max leans toward long-horizon agentic coding (swe-bench pro 60.6, terminal-bench 2.0 69.7), and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Fugu Ultra v2.0 or Qwen 3.7 Max?

Qwen 3.7 Max is cheaper — $5/$30 per 1M tokens vs $2.5/$7.5 per 1M tokens, roughly 2× apart on input.

Which has the bigger context window?

Both advertise 1M tokens (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.

Can I use both Fugu Ultra v2.0 and Qwen 3.7 Max together?

Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Qwen 3.7 Max and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.

Which is newer, Fugu Ultra v2.0 or Qwen 3.7 Max?

Fugu Ultra v2.0 — released September 10, 2026, about 4 months after Qwen 3.7 Max.

Related comparisons

Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.