Fugu Ultra v2.0 vs Gemini 3.1 Pro

Sakana AI · Global  |  Google · 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 Gemini 3.1 Pro for full multimodal input — text, image, audio and video in one 1m-token window or long video and document analysis. On a tight budget at scale, Gemini 3.1 Pro is the value pick.

Fugu Ultra v2.0 (Sakana AI) and Gemini 3.1 Pro (Google) 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. Gemini 3.1 Pro is a 1M-token multimodal workhorse — huge breadth across text, image, audio and video, but recall fades deep in the window. 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 v2.0Gemini 3.1 Pro
ProviderSakana AI (Global) Google (US)
ReleasedSeptember 10, 2026 February 19, 2026
Context window1M tokens (~1,500 pages) 1M (~1,573 pages)
Price (in/out)$5/$30 per 1M tokens $2/$12 per 1M tokens
Open weight?No — API only No — API only
Modalitiestext text, image, audio, video, code
SWE-Bench VerifiedNot published Not published
MRCR v2 @ 1MNot published 26.3%

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; Gemini 3.1 Pro does not.

1M-token context window

Fugu Ultra v2.0

Gemini 3.1 Pro is comparatively weak here — long-context recall drops sharply past 256K (26.3% on MRCR v2 at 1M)

Full multimodal input — text, image, audio and video in one 1M-token window

Gemini 3.1 Pro

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

Long video and document analysis

Gemini 3.1 Pro

A 1M-token multimodal workhorse — huge breadth across text, image, audio and video, but recall fades deep in the window — and it runs cheaper at $2/$12 per 1M tokens.

Agentic reasoning (high ARC-AGI-2)

Gemini 3.1 Pro

Gemini 3.1 Pro lists agentic reasoning (high ARC-AGI-2) among its strengths; Fugu Ultra v2.0 does not.

Lowest cost at scale

Gemini 3.1 Pro

At $2/$12 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

Gemini 3.1 Pro

At $2/$12 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.

Someone analysing very long documents or codebases

Gemini 3.1 Pro

Larger 1M 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 full multimodal input — text, image, audio and video in one 1m-token window

Gemini 3.1 Pro

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.

Gemini 3.1 Pro: where it fits

A 1M-token multimodal workhorse — huge breadth across text, image, audio and video, but recall fades deep in the window. Released February 19, 2026 by Google, it is built for full multimodal input — text, image, audio and video in one 1M-token window, long video and document analysis, agentic reasoning (high ARC-AGI-2), and broad multimodal understanding across formats.

Its trade-offs: long-context recall drops sharply past 256K (26.3% on MRCR v2 at 1M), premium price per token at $2/$12, and superseded within Google's own line by the newer 3.5/3.6 Flash releases for cost-sensitive work. At $2 in / $12 out per million tokens, it sits in the mid price band.

The bottom line for this matchup

Fugu Ultra v2.0 and Gemini 3.1 Pro overlap enough that the right pick depends on your specific job. Gemini 3.1 Pro costs less per token; Gemini 3.1 Pro 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, Gemini 3.1 Pro for full multimodal input — text, image, audio and video in one 1m-token window. Rather than crowning one, run the same hard task through both once and let the results decide.

Want both Fugu Ultra v2.0 and Gemini 3.1 Pro 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 Gemini 3.1 Pro 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 Gemini 3.1 Pro leans toward full multimodal input — text, image, audio and video in one 1m-token window, and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Fugu Ultra v2.0 or Gemini 3.1 Pro?

Gemini 3.1 Pro is cheaper — $5/$30 per 1M tokens vs $2/$12 per 1M tokens, roughly 2.5× apart on input.

Which has the bigger context window?

Effectively neither — 1M tokens vs 1M is a difference of a few percent. Remember advertised ≠ usable: recall typically degrades before the ceiling.

Can I use both Fugu Ultra v2.0 and Gemini 3.1 Pro together?

Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Gemini 3.1 Pro 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 Gemini 3.1 Pro?

Fugu Ultra v2.0 — released September 10, 2026, about 7 months after Gemini 3.1 Pro.

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.