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 GPT-5.6 Luna for cheapest gpt-5.6 tier for high-volume drafting and automation or fast, affordable execution while keeping respectable coding. On a tight budget at scale, GPT-5.6 Luna is the value pick.
Fugu Ultra v2.0 (Sakana AI) and GPT-5.6 Luna (OpenAI) 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. GPT-5.6 Luna is the budget, high-throughput GPT-5.6 tier — built for cheap, fast, large-volume work rather than deep long-context reasoning. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.
Key differences
Price: GPT-5.6 Luna is about 5× cheaper on input ($1/$6 per 1M tokens vs $5/$30 per 1M tokens) — a large enough gap that at scale it can be the single biggest line item in the decision.
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: Fugu Ultra v2.0 is the newer model by about 2 months (released September 10, 2026), usually meaning fresher training data and capabilities.
Specifications
Spec
Fugu Ultra v2.0
GPT-5.6 Luna
Provider
Sakana AI (Global)
OpenAI (US)
Released
September 10, 2026
July 9, 2026
Context window
1M tokens (~1,500 pages)
1M (~1,500 pages)
Price (in/out)
$5/$30 per 1M tokens
$1/$6 per 1M tokens
Open weight?
No — API only
No — API only
Modalities
text
text, image, 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 — 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; GPT-5.6 Luna does not.
1M-token context window: Fugu Ultra v2.0 — GPT-5.6 Luna is comparatively weak here — weak long-context recall deep in its 1M window (MRCR far below Sol)
Cheapest GPT-5.6 tier for high-volume drafting and automation: GPT-5.6 Luna — At $1/$6 per 1M tokens it undercuts Fugu Ultra v2.0 ($5/$30 per 1M tokens), and that gap compounds at volume.
Fast, affordable execution while keeping respectable coding: GPT-5.6 Luna — The budget, high-throughput GPT-5.6 tier — built for cheap, fast, large-volume work rather than deep long-context reasoning — and it runs cheaper at $1/$6 per 1M tokens.
Same 1M context and programmatic tool calling as its siblings: GPT-5.6 Luna — GPT-5.6 Luna lists same 1M context and programmatic tool calling as its siblings among its strengths; Fugu Ultra v2.0 does not.
Lowest cost at scale: GPT-5.6 Luna — At $1/$6 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: GPT-5.6 Luna — At $1/$6 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 cheapest gpt-5.6 tier for high-volume drafting and automation: GPT-5.6 Luna — 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.
GPT-5.6 Luna: where it fits
The budget, high-throughput GPT-5.6 tier — built for cheap, fast, large-volume work rather than deep long-context reasoning. Released July 9, 2026 by OpenAI, it is built for cheapest GPT-5.6 tier for high-volume drafting and automation, fast, affordable execution while keeping respectable coding, same 1M context and programmatic tool calling as its siblings, and high-throughput simple agentic jobs.
Its trade-offs: weak long-context recall deep in its 1M window (MRCR far below Sol), and lowest raw capability of the three GPT-5.6 tiers; no open weights. At $1 in / $6 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
Fugu Ultra v2.0 and GPT-5.6 Luna overlap enough that the right pick depends on your specific job. GPT-5.6 Luna 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, GPT-5.6 Luna for cheapest gpt-5.6 tier for high-volume drafting and automation. Rather than crowning one, run the same hard task through both once and let the results decide.
Frequently asked questions
Is Fugu Ultra v2.0 or GPT-5.6 Luna 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 GPT-5.6 Luna leans toward cheapest gpt-5.6 tier for high-volume drafting and automation, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or GPT-5.6 Luna?
GPT-5.6 Luna is cheaper — $5/$30 per 1M tokens vs $1/$6 per 1M tokens, roughly 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 GPT-5.6 Luna together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, GPT-5.6 Luna 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 GPT-5.6 Luna?
Fugu Ultra v2.0 — released September 10, 2026, about 2 months after GPT-5.6 Luna.
Fugu Ultra v2.0 vs GPT-5.6 Luna
Sakana AI · Global | OpenAI · 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 GPT-5.6 Luna for cheapest gpt-5.6 tier for high-volume drafting and automation or fast, affordable execution while keeping respectable coding. On a tight budget at scale, GPT-5.6 Luna is the value pick.
Fugu Ultra v2.0 (Sakana AI) and GPT-5.6 Luna (OpenAI) 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. GPT-5.6 Luna is the budget, high-throughput GPT-5.6 tier — built for cheap, fast, large-volume work rather than deep long-context reasoning. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.
Key differences at a glance
▸Price: GPT-5.6 Luna is about 5× cheaper on input ($1/$6 per 1M tokens vs $5/$30 per 1M tokens) — a large enough gap that at scale it can be the single biggest line item in the decision.
▸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: Fugu Ultra v2.0 is the newer model by about 2 months (released September 10, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
Spec
Fugu Ultra v2.0
GPT-5.6 Luna
Provider
Sakana AI (Global)
OpenAI (US)
Released
September 10, 2026
July 9, 2026
Context window
1M tokens (~1,500 pages)
1M (~1,500 pages)
Price (in/out)
$5/$30 per 1M tokens
$1/$6 per 1M tokens
Open weight?
No — API only
No — API only
Modalities
text
text, image, 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
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; GPT-5.6 Luna does not.
1M-token context window
Fugu Ultra v2.0
GPT-5.6 Luna is comparatively weak here — weak long-context recall deep in its 1M window (MRCR far below Sol)
Cheapest GPT-5.6 tier for high-volume drafting and automation
GPT-5.6 Luna
At $1/$6 per 1M tokens it undercuts Fugu Ultra v2.0 ($5/$30 per 1M tokens), and that gap compounds at volume.
Fast, affordable execution while keeping respectable coding
GPT-5.6 Luna
The budget, high-throughput GPT-5.6 tier — built for cheap, fast, large-volume work rather than deep long-context reasoning — and it runs cheaper at $1/$6 per 1M tokens.
Same 1M context and programmatic tool calling as its siblings
GPT-5.6 Luna
GPT-5.6 Luna lists same 1M context and programmatic tool calling as its siblings among its strengths; Fugu Ultra v2.0 does not.
Lowest cost at scale
GPT-5.6 Luna
At $1/$6 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
→ GPT-5.6 Luna
At $1/$6 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 cheapest gpt-5.6 tier for high-volume drafting and automation
→ GPT-5.6 Luna
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.
GPT-5.6 Luna: where it fits
The budget, high-throughput GPT-5.6 tier — built for cheap, fast, large-volume work rather than deep long-context reasoning. Released July 9, 2026 by OpenAI, it is built for cheapest GPT-5.6 tier for high-volume drafting and automation, fast, affordable execution while keeping respectable coding, same 1M context and programmatic tool calling as its siblings, and high-throughput simple agentic jobs.
Its trade-offs: weak long-context recall deep in its 1M window (MRCR far below Sol), and lowest raw capability of the three GPT-5.6 tiers; no open weights. At $1 in / $6 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
Fugu Ultra v2.0 and GPT-5.6 Luna overlap enough that the right pick depends on your specific job. GPT-5.6 Luna 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, GPT-5.6 Luna for cheapest gpt-5.6 tier for high-volume drafting and automation. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both Fugu Ultra v2.0 and GPT-5.6 Luna 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.
Is Fugu Ultra v2.0 or GPT-5.6 Luna 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 GPT-5.6 Luna leans toward cheapest gpt-5.6 tier for high-volume drafting and automation, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or GPT-5.6 Luna?
GPT-5.6 Luna is cheaper — $5/$30 per 1M tokens vs $1/$6 per 1M tokens, roughly 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 GPT-5.6 Luna together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, GPT-5.6 Luna 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 GPT-5.6 Luna?
Fugu Ultra v2.0 — released September 10, 2026, about 2 months after GPT-5.6 Luna.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.