Fugu Ultra v2.0 vs MAI-Thinking-1

Sakana AI · Global  |  Microsoft · US · 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 MAI-Thinking-1 for very strong math reasoning (aime 2025 97%, aime 2026 94.5%) or microsoft's first in-house flagship reasoner, trained without openai distillation. On a tight budget at scale, MAI-Thinking-1 is the value pick.

Fugu Ultra v2.0 (Sakana AI) and MAI-Thinking-1 (Microsoft) 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. MAI-Thinking-1 is microsoft's first fully in-house flagship reasoning model — a Claude-class reasoner built independently to cut its OpenAI dependence. They diverge most on price and context window — each quantified below from the models' real specs.

Key differences at a glance

Side-by-side specs

SpecFugu Ultra v2.0MAI-Thinking-1
ProviderSakana AI (Global) Microsoft (US)
ReleasedSeptember 10, 2026 August 12, 2026
Context window1M tokens (~1,500 pages) 256K (~384 pages)
Price (in/out)$5/$30 per 1M tokens Not published
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

MAI-Thinking-1 is comparatively weak here — benchmarks are largely self-reported

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

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 carries the larger 1M tokens context.

1M-token context window

Fugu Ultra v2.0

Its 1M tokens window holds about 3.9× more than MAI-Thinking-1's 256K in a single prompt.

Very strong math reasoning (AIME 2025 97%, AIME 2026 94.5%)

MAI-Thinking-1

MAI-Thinking-1 lists very strong math reasoning (AIME 2025 97%, AIME 2026 94.5%) among its strengths; Fugu Ultra v2.0 does not.

Microsoft's first in-house flagship reasoner, trained without OpenAI distillation

MAI-Thinking-1

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

Efficient reasoning at low token cost for its class

MAI-Thinking-1

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

Lowest cost at scale

MAI-Thinking-1

Its weights are open, so at volume you pay for your own hardware instead of Fugu Ultra v2.0's $5/$30 per 1M tokens.

Largest single-prompt input

Fugu Ultra v2.0

Its 1M tokens window is about 3.9× larger than MAI-Thinking-1's 256K, fitting roughly 1,500 pages in one prompt.

Which should you pick?

A cost-sensitive startup shipping high volume

MAI-Thinking-1

At Not published it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.

Someone analysing very long documents or codebases

Fugu Ultra v2.0

Larger 1M tokens window fits more in one prompt.

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 very strong math reasoning (aime 2025 97%, aime 2026 94.5%)

MAI-Thinking-1

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.

MAI-Thinking-1: where it fits

Microsoft's first fully in-house flagship reasoning model — a Claude-class reasoner built independently to cut its OpenAI dependence. Released August 12, 2026 by Microsoft, it is built for very strong math reasoning (AIME 2025 97%, AIME 2026 94.5%), microsoft's first in-house flagship reasoner, trained without OpenAI distillation, efficient reasoning at low token cost for its class, and competitive with Claude Opus 4.6 on SWE-Bench Pro (vendor-reported).

Its trade-offs: closed and in private preview — no open weights, no published pricing, thin availability, and benchmarks are largely self-reported.

The bottom line for this matchup

Fugu Ultra v2.0 and MAI-Thinking-1 overlap enough that the right pick depends on your specific job. MAI-Thinking-1 costs less per token; Fugu Ultra v2.0 holds the larger context; 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, MAI-Thinking-1 for very strong math reasoning (aime 2025 97%, aime 2026 94.5%). Rather than crowning one, run the same hard task through both once and let the results decide.

Want both Fugu Ultra v2.0 and MAI-Thinking-1 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 MAI-Thinking-1 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 MAI-Thinking-1 leans toward very strong math reasoning (aime 2025 97%, aime 2026 94.5%), and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Fugu Ultra v2.0 or MAI-Thinking-1?

MAI-Thinking-1 is cheaper — $5/$30 per 1M tokens vs Not published.

Which has the bigger context window?

Fugu Ultra v2.0 — 1M tokens vs 256K, about 3.9× larger. Useful only if the model actually reasons over the full window, which not all do.

Can I use both Fugu Ultra v2.0 and MAI-Thinking-1 together?

Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, MAI-Thinking-1 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 MAI-Thinking-1?

Fugu Ultra v2.0 — released September 10, 2026, about 29 days after MAI-Thinking-1.

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.