Claude Sonnet 5 vs Fugu Ultra v2.0

Anthropic · US  |  Sakana AI · Global · Updated June 2026

Quick verdict

Pick Claude Sonnet 5 for agentic workflows that plan, use tools, and run autonomously or multi-step coding, debugging, and tool use. 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. On a tight budget at scale, Claude Sonnet 5 is the value pick.

Claude Sonnet 5 (Anthropic) and Fugu Ultra v2.0 (Sakana AI) are two of the models people most often weigh against each other in 2026. Claude Sonnet 5 is anthropic's most agentic Sonnet, with near-Opus-4.8 performance at Sonnet prices; the default model on Free and Pro. 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. 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

SpecClaude Sonnet 5Fugu Ultra v2.0
ProviderAnthropic (US) Sakana AI (Global)
ReleasedJune 30, 2026 September 10, 2026
Context window1M (~1,500 pages) 1M tokens (~1,500 pages)
Price (in/out)$2/$10 per 1M tokens $5/$30 per 1M tokens
Open weight?No — API only No — API only
Modalitiestext, image, code text
SWE-Bench VerifiedNot published Not published
MRCR v2 @ 1MNot published Not published

Who wins what

Agentic workflows that plan, use tools, and run autonomously

Claude Sonnet 5

Anthropic's most agentic Sonnet, with near-Opus-4.8 performance at Sonnet prices; the default model on Free and Pro — and it runs cheaper at $2/$10 per 1M tokens.

Multi-step coding, debugging, and tool use

Claude Sonnet 5

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

Everyday professional and knowledge work

Claude Sonnet 5

Claude Sonnet 5 lists everyday professional and knowledge work among its strengths; Fugu Ultra v2.0 does not.

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; Claude Sonnet 5 does not.

1M-token context window

Fugu Ultra v2.0

Claude Sonnet 5 is comparatively weak here — an updated tokenizer that can use 1.0-1.35x more tokens for the same text

Lowest cost at scale

Claude Sonnet 5

At $2/$10 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

Claude Sonnet 5

At $2/$10 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.

Anyone whose priority is agentic workflows that plan, use tools, and run autonomously

Claude Sonnet 5

It is specifically built for that.

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

That is its strongest area.

Claude Sonnet 5: where it fits

Anthropic's most agentic Sonnet, with near-Opus-4.8 performance at Sonnet prices; the default model on Free and Pro. Released June 30, 2026 by Anthropic, it is built for agentic workflows that plan, use tools, and run autonomously, multi-step coding, debugging, and tool use, everyday professional and knowledge work, and long-document analysis and reasoning.

Its trade-offs are real: lower peak accuracy than Opus 4.8 on the hardest tasks, and an updated tokenizer that can use 1.0-1.35x more tokens for the same text. At $2 in / $10 out per million tokens, it sits in the mid price band.

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: 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.

The bottom line for this matchup

Claude Sonnet 5 and Fugu Ultra v2.0 overlap enough that the right pick depends on your specific job. Claude Sonnet 5 costs less per token; and each leads in its own area — Claude Sonnet 5 for agentic workflows that plan, use tools, and run autonomously, 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. Rather than crowning one, run the same hard task through both once and let the results decide.

Want both Claude Sonnet 5 and Fugu Ultra v2.0 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 Claude Sonnet 5 or Fugu Ultra v2.0 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, Claude Sonnet 5 leans toward agentic workflows that plan, use tools, and run autonomously while 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, and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Claude Sonnet 5 or Fugu Ultra v2.0?

Claude Sonnet 5 is cheaper — $2/$10 per 1M tokens vs $5/$30 per 1M tokens, roughly 2.5× apart on input.

Which has the bigger context window?

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

Can I use both Claude Sonnet 5 and Fugu Ultra v2.0 together?

Yes — a multi-model platform like LumiChats gives you Claude Sonnet 5, Fugu Ultra v2.0 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, Claude Sonnet 5 or Fugu Ultra v2.0?

Fugu Ultra v2.0 — released September 10, 2026, about 2 months after Claude Sonnet 5.

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.