Fugu Ultra v2.0 vs Qwen 3.7 Plus

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 Plus for reading screens and interacting with guis or generating code from visual references. On a tight budget at scale, Qwen 3.7 Plus is the value pick.

Fugu Ultra v2.0 (Sakana AI) and Qwen 3.7 Plus (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 Plus is alibaba's cost-effective multimodal agent in the Qwen3.7 series, built to perceive scenes, read screens and GUIs, generate code from visual references, and navigate mobile apps end-to-end. 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 Plus
ProviderSakana AI (Global) Alibaba (China)
ReleasedSeptember 10, 2026 June 1, 2026
Context window1M tokens (~1,500 pages) 1M (~1,500 pages)
Price (in/out)$5/$30 per 1M tokens $0.4/$1.6 per 1M tokens
Open weight?No — API only No — API only
Modalitiestext text, image, video, 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

Fugu Ultra v2.0 lists claims to outperform flagship models like GPT-6 Astra and Claude Fable 5.1 despite its underlying orchestration pool reportedly excluding both of them among its strengths; Qwen 3.7 Plus does not.

1M-token context window

Fugu Ultra v2.0

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

Reading screens and interacting with GUIs

Qwen 3.7 Plus

Alibaba's cost-effective multimodal agent in the Qwen3.7 series, built to perceive scenes, read screens and GUIs, generate code from visual references, and navigate mobile apps end-to-end — and it runs cheaper at $0.4/$1.6 per 1M tokens.

Generating code from visual references

Qwen 3.7 Plus

Qwen 3.7 Plus lists generating code from visual references among its strengths; Fugu Ultra v2.0 does not.

Agentic tool use, verification, and autonomous iteration

Qwen 3.7 Plus

Qwen 3.7 Plus lists agentic tool use, verification, and autonomous iteration among its strengths; Fugu Ultra v2.0 does not.

Lowest cost at scale

Qwen 3.7 Plus

At $0.4/$1.6 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 Plus

At $0.4/$1.6 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 reading screens and interacting with guis

Qwen 3.7 Plus

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 Plus: where it fits

Alibaba's cost-effective multimodal agent in the Qwen3.7 series, built to perceive scenes, read screens and GUIs, generate code from visual references, and navigate mobile apps end-to-end. Released June 1, 2026 by Alibaba, it is built for reading screens and interacting with GUIs, generating code from visual references, agentic tool use, verification, and autonomous iteration, and cost-effective vision-language processing at 1M context.

Its trade-offs: proprietary and API-only, with no downloadable weights, and outputs text only, no image, audio, or video generation. At $0.4 in / $1.6 out per million tokens, it sits in the budget price band.

The bottom line for this matchup

Fugu Ultra v2.0 and Qwen 3.7 Plus overlap enough that the right pick depends on your specific job. Qwen 3.7 Plus 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 Plus for reading screens and interacting with guis. 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 Plus 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 Plus 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 Plus leans toward reading screens and interacting with guis, and that positioning usually predicts which feels better on your codebase.

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

Qwen 3.7 Plus is cheaper — $5/$30 per 1M tokens vs $0.4/$1.6 per 1M tokens, roughly 13× 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 Plus together?

Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Qwen 3.7 Plus 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 Plus?

Fugu Ultra v2.0 — released September 10, 2026, about 3 months after Qwen 3.7 Plus.

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.