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 Hunyuan Hy4 Preview for gpqa diamond (92.3) or terminal-bench (85.4). Choose Hunyuan Hy4 Preview if you need self-hosting or data privacy; Fugu Ultra v2.0 if you want a managed API.
Fugu Ultra v2.0 (Sakana AI) and Hunyuan Hy4 Preview (Tencent) 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. Hunyuan Hy4 Preview is tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. They diverge most on price and open vs. closed weights — each quantified below from the models' real specs.
Key differences
Price: Hunyuan Hy4 Preview is about 6× cheaper on input ($0.834/$2.501 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.
Specifications
Spec
Fugu Ultra v2.0
Hunyuan Hy4 Preview
Provider
Sakana AI (Global)
Tencent (China)
Released
September 10, 2026
August 28, 2026
Context window
1M tokens (~1,500 pages)
1M+ tokens (~1,500 pages)
Price (in/out)
$5/$30 per 1M tokens
$0.834/$2.501 per 1M tokens
Open weight?
No — API only
Yes — self-hostable
Modalities
text
text
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 — Hunyuan Hy4 Preview is comparatively weak here — labeled a 'preview', not yet Tencent's finalized GA flagship
1M-token context window: Fugu Ultra v2.0 — Fugu Ultra v2.0 lists 1M-token context window among its strengths; Hunyuan Hy4 Preview does not.
GPQA Diamond (92.3): Hunyuan Hy4 Preview — Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and it runs cheaper at $0.834/$2.501 per 1M tokens.
Terminal-Bench (85.4): Hunyuan Hy4 Preview — 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
SWE-bench Multilingual (82.9): Hunyuan Hy4 Preview — Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and its weights are open while Fugu Ultra v2.0 is API-only.
Lowest cost at scale: Hunyuan Hy4 Preview — At $0.834/$2.501 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: Hunyuan Hy4 Preview — At $0.834/$2.501 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.
A team with data-privacy or self-hosting needs: Hunyuan Hy4 Preview — Open weights let you run it on your own hardware; Fugu Ultra v2.0 is API-only.
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 gpqa diamond (92.3): Hunyuan Hy4 Preview — 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.
Hunyuan Hy4 Preview: where it fits
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. Released August 28, 2026 by Tencent, it is built for gPQA Diamond (92.3), terminal-Bench (85.4), sWE-bench Multilingual (82.9), and large jump in long-horizon coding vs prior Hunyuan model (DeepSWE 28.0 to 64.3).
Its trade-offs: text-only, no native vision support, labeled a 'preview', not yet Tencent's finalized GA flagship, and sWE-Marathon score still low in absolute terms (31.9) despite a large relative jump. At $0.834 in / $2.501 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. Hunyuan Hy4 Preview gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Fugu Ultra v2.0 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Frequently asked questions
Is Fugu Ultra v2.0 or Hunyuan Hy4 Preview 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 Hunyuan Hy4 Preview leans toward gpqa diamond (92.3), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or Hunyuan Hy4 Preview?
Hunyuan Hy4 Preview is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Fugu Ultra v2.0 is API-metered at $5/$30 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
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 Hunyuan Hy4 Preview together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Hunyuan Hy4 Preview 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 Hunyuan Hy4 Preview?
Fugu Ultra v2.0 — released September 10, 2026, about 13 days after Hunyuan Hy4 Preview.
Fugu Ultra v2.0 vs Hunyuan Hy4 Preview
Sakana AI · Global | Tencent · China · 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 Hunyuan Hy4 Preview for gpqa diamond (92.3) or terminal-bench (85.4). Choose Hunyuan Hy4 Preview if you need self-hosting or data privacy; Fugu Ultra v2.0 if you want a managed API.
Fugu Ultra v2.0 (Sakana AI) and Hunyuan Hy4 Preview (Tencent) 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. Hunyuan Hy4 Preview is tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. They diverge most on price and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
▸Price: Hunyuan Hy4 Preview is about 6× cheaper on input ($0.834/$2.501 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.
Side-by-side specs
Spec
Fugu Ultra v2.0
Hunyuan Hy4 Preview
Provider
Sakana AI (Global)
Tencent (China)
Released
September 10, 2026
August 28, 2026
Context window
1M tokens (~1,500 pages)
1M+ tokens (~1,500 pages)
Price (in/out)
$5/$30 per 1M tokens
$0.834/$2.501 per 1M tokens
Open weight?
No — API only
Yes — self-hostable
Modalities
text
text
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
Hunyuan Hy4 Preview is comparatively weak here — labeled a 'preview', not yet Tencent's finalized GA flagship
1M-token context window
Fugu Ultra v2.0
Fugu Ultra v2.0 lists 1M-token context window among its strengths; Hunyuan Hy4 Preview does not.
GPQA Diamond (92.3)
Hunyuan Hy4 Preview
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and it runs cheaper at $0.834/$2.501 per 1M tokens.
Terminal-Bench (85.4)
Hunyuan Hy4 Preview
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
SWE-bench Multilingual (82.9)
Hunyuan Hy4 Preview
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and its weights are open while Fugu Ultra v2.0 is API-only.
Lowest cost at scale
Hunyuan Hy4 Preview
At $0.834/$2.501 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
→ Hunyuan Hy4 Preview
At $0.834/$2.501 per 1M tokens it undercuts Fugu Ultra v2.0, and on millions of tokens that margin decides the monthly bill.
A team with data-privacy or self-hosting needs
→ Hunyuan Hy4 Preview
Open weights let you run it on your own hardware; Fugu Ultra v2.0 is API-only.
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 gpqa diamond (92.3)
→ Hunyuan Hy4 Preview
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.
Hunyuan Hy4 Preview: where it fits
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. Released August 28, 2026 by Tencent, it is built for gPQA Diamond (92.3), terminal-Bench (85.4), sWE-bench Multilingual (82.9), and large jump in long-horizon coding vs prior Hunyuan model (DeepSWE 28.0 to 64.3).
Its trade-offs: text-only, no native vision support, labeled a 'preview', not yet Tencent's finalized GA flagship, and sWE-Marathon score still low in absolute terms (31.9) despite a large relative jump. At $0.834 in / $2.501 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. Hunyuan Hy4 Preview gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Fugu Ultra v2.0 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Fugu Ultra v2.0 and Hunyuan Hy4 Preview 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 Hunyuan Hy4 Preview 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 Hunyuan Hy4 Preview leans toward gpqa diamond (92.3), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or Hunyuan Hy4 Preview?
Hunyuan Hy4 Preview is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Fugu Ultra v2.0 is API-metered at $5/$30 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
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 Hunyuan Hy4 Preview together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Hunyuan Hy4 Preview 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 Hunyuan Hy4 Preview?
Fugu Ultra v2.0 — released September 10, 2026, about 13 days after Hunyuan Hy4 Preview.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.