Fugu Ultra v2.0 vs Gemini 4 Carbon
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 4 Carbon for ranked first on the artificial analysis intelligence index v5.0 with 59 at launch (artificial analysis now shows 60) or google-reported 88.2% on sec-bench pro and 54.8% on exploitgym for vulnerability discovery and exploit validation. On a tight budget at scale, Gemini 4 Carbon is the value pick.
Fugu Ultra v2.0 (Sakana AI) and Gemini 4 Carbon (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 4 Carbon is google's October 28, 2026 limited release for cyber defenders - top of the Artificial Analysis index at launch, priced at $2/$10 introductory, with no public API date yet. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.
Key differences at a glance
- ▸Price: Gemini 4 Carbon is about 2.5× cheaper on input ($2/$10 per 1M tokens vs $5/$30 per 1M tokens) — meaningful once you are processing millions of tokens a month.
- ▸Context window: both advertise 1M tokens (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
- ▸Recency: Gemini 4 Carbon is the newer model by about 48 days (released October 28, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Fugu Ultra v2.0 | Gemini 4 Carbon |
|---|---|---|
| Provider | Sakana AI (Global) | Google (US) |
| Released | September 10, 2026 | October 28, 2026 |
| Context window | 1M tokens (~1,500 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | $5/$30 per 1M tokens | $2/$10 per 1M tokens |
| Open weight? | No — API only | No — API only |
| Modalities | text | text, image, audio, video, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not 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
Fugu Ultra v2.0 lists 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 among its strengths; Gemini 4 Carbon does not.
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 4 Carbon does not.
1M-token context window
Fugu Ultra v2.0
Gemini 4 Carbon is comparatively weak here — google has not published context or modality specs - the 1M window and modalities shown come from Artificial Analysis and Vals
Ranked first on the Artificial Analysis Intelligence Index v5.0 with 59 at launch (Artificial Analysis now shows 60)
Gemini 4 Carbon
Google's October 28, 2026 limited release for cyber defenders - top of the Artificial Analysis index at launch, priced at $2/$10 introductory, with no public API date yet — and it runs cheaper at $2/$10 per 1M tokens.
Google-reported 88.2% on SEC-bench Pro and 54.8% on ExploitGym for vulnerability discovery and exploit validation
Gemini 4 Carbon
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
Google-reported 71.0% on CWE-bench for patching
Gemini 4 Carbon
Google's October 28, 2026 limited release for cyber defenders - top of the Artificial Analysis index at launch, priced at $2/$10 introductory, with no public API date yet — and it is the newer of the two.
Lowest cost at scale
Gemini 4 Carbon
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
→ Gemini 4 Carbon
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 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 ranked first on the artificial analysis intelligence index v5.0 with 59 at launch (artificial analysis now shows 60)
→ Gemini 4 Carbon
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 4 Carbon: where it fits
Google's October 28, 2026 limited release for cyber defenders - top of the Artificial Analysis index at launch, priced at $2/$10 introductory, with no public API date yet. Released October 28, 2026 by Google, it is built for ranked first on the Artificial Analysis Intelligence Index v5.0 with 59 at launch (Artificial Analysis now shows 60), google-reported 88.2% on SEC-bench Pro and 54.8% on ExploitGym for vulnerability discovery and exploit validation, google-reported 71.0% on CWE-bench for patching, and introductory $2/$10 per million tokens, matching Gemini 4 Argon, with cached input 95% off.
Its trade-offs: limited release: rolling out to a subset of cyber defenders, then trusted partners via the Fairwind Program, with no date for developers or consumers, no public API model listing yet, so most users cannot call it today, introductory pricing rises to $4/$20 afterward, and Google has not said when that happens, and google has not published context or modality specs - the 1M window and modalities shown come from Artificial Analysis and Vals. At $2 in / $10 out per million tokens, it sits in the mid price band.
The bottom line for this matchup
Fugu Ultra v2.0 and Gemini 4 Carbon overlap enough that the right pick depends on your specific job. Gemini 4 Carbon 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, Gemini 4 Carbon for ranked first on the artificial analysis intelligence index v5.0 with 59 at launch (artificial analysis now shows 60). 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 4 Carbon 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 pricingFrequently asked questions
Is Fugu Ultra v2.0 or Gemini 4 Carbon 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 4 Carbon leans toward ranked first on the artificial analysis intelligence index v5.0 with 59 at launch (artificial analysis now shows 60), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or Gemini 4 Carbon?
Gemini 4 Carbon is cheaper — $5/$30 per 1M tokens vs $2/$10 per 1M tokens, roughly 2.5× 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 Gemini 4 Carbon together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Gemini 4 Carbon 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 4 Carbon?
Gemini 4 Carbon — released October 28, 2026, about 48 days after Fugu Ultra v2.0.
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.