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.

Qwen3 235B A22B (2507): where it fits

An older 235B text-only open mixture-of-experts with broad knowledge and strong writing — but no vision, no thinking mode, and weak coding. Released July 21, 2025 by Alibaba, it is built for deep world knowledge from 235B total parameters (83.0 MMLU-Pro, 93.1 MMLU-Redux), exceptional multilingual and alignment results (79.2 Arena-Hard v2, 85.2 WritingBench), outstanding structured logic — 95.0 on ZebraLogic, and no thinking mode, which makes latency and token spend entirely predictable.

Its trade-offs: nearly a year old and superseded — Artificial Analysis now steers users to Qwen3.5-397B instead, text-only with no vision, and the absence of a thinking mode caps its hardest reasoning, coding is weak by 2026 standards, and it publishes no SWE-Bench score to compare on, and its 235B weights need roughly 438GB in BF16, far beyond consumer hardware. As an open-weight model, its running cost is your own hardware rather than a per-token fee.

The bottom line for this matchup

The defining split here is open vs. closed. Qwen3 235B A22B (2507) gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Fugu Ultra v2.0 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.

Related comparisons