Fugu Ultra v2.0 vs Hunyuan Hy4
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 for first hunyuan model with vision and computer use, adding image input to the text-only hy4 preview or tencent-reported gains over the preview of 19.1% on gamedev and 9.8% on gamelogic. On a tight budget at scale, Hunyuan Hy4 is the value pick.
Fugu Ultra v2.0 (Sakana AI) and Hunyuan Hy4 (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 is tencent's November 4, 2026 full Hy4 release - a 1M-context model that adds vision and computer use at about $0.90/$2.70, with weights promised but not yet public. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: Hunyuan Hy4 is about 5.6× cheaper on input ($0.9/$2.7 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: 1M tokens vs 1M tokens — within a few percent of each other, so treat this as a tie and test on your own long inputs, since usable recall varies by model.
- ▸Recency: Hunyuan Hy4 is the newer model by about 55 days (released November 4, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Fugu Ultra v2.0 | Hunyuan Hy4 |
|---|---|---|
| Provider | Sakana AI (Global) | Tencent (China) |
| Released | September 10, 2026 | November 4, 2026 |
| Context window | 1M tokens (~1,500 pages) | 1M tokens (~1,573 pages) |
| Price (in/out) | $5/$30 per 1M tokens | $0.9/$2.7 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
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; Hunyuan Hy4 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; Hunyuan Hy4 does not.
1M-token context window
Fugu Ultra v2.0
Fugu Ultra v2.0 lists 1M-token context window among its strengths; Hunyuan Hy4 does not.
First Hunyuan model with vision and computer use, adding image input to the text-only Hy4 Preview
Hunyuan Hy4
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
Tencent-reported gains over the preview of 19.1% on GameDev and 9.8% on GameLogic
Hunyuan Hy4
Tencent's November 4, 2026 full Hy4 release - a 1M-context model that adds vision and computer use at about $0.90/$2.70, with weights promised but not yet public — and it runs cheaper at $0.9/$2.7 per 1M tokens.
Tencent-reported financial evaluation of 3.04, ahead of DeepSeek V4.1 Flash 1017 at 2.97
Hunyuan Hy4
Fugu Ultra v2.0 is comparatively weak here — 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
Lowest cost at scale
Hunyuan Hy4
At $0.9/$2.7 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
At $0.9/$2.7 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
→ Hunyuan Hy4
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 first hunyuan model with vision and computer use, adding image input to the text-only hy4 preview
→ Hunyuan Hy4
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: where it fits
Tencent's November 4, 2026 full Hy4 release - a 1M-context model that adds vision and computer use at about $0.90/$2.70, with weights promised but not yet public. Released November 4, 2026 by Tencent, it is built for first Hunyuan model with vision and computer use, adding image input to the text-only Hy4 Preview, tencent-reported gains over the preview of 19.1% on GameDev and 9.8% on GameLogic, tencent-reported financial evaluation of 3.04, ahead of DeepSeek V4.1 Flash 1017 at 2.97, and about $0.90/$2.70 per million tokens, with 50% off on Tencent Cloud TokenHub through December 31, 2026 (OpenRouter lists $0.417/$1.25 with that discount).
Its trade-offs: weights not public as of November 5, 2026 - Tencent says weights and system cards will come in the coming days, and no license is announced yet, only the earlier Hy4 Preview is downloadable today (Apache 2.0), published improvements are Tencent's own and mostly relative to the preview, with no SWE-bench Verified figure, and sources differ on list price: Tencent says about $0.90/$2.70, while OpenRouter and Vals show $0.83/$2.50. At $0.9 in / $2.7 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
Fugu Ultra v2.0 and Hunyuan Hy4 overlap enough that the right pick depends on your specific job. Hunyuan Hy4 costs less per token; Hunyuan Hy4 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, Hunyuan Hy4 for first hunyuan model with vision and computer use, adding image input to the text-only hy4 preview. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both Fugu Ultra v2.0 and Hunyuan Hy4 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 Hunyuan Hy4 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 leans toward first hunyuan model with vision and computer use, adding image input to the text-only hy4 preview, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or Hunyuan Hy4?
Hunyuan Hy4 is cheaper — $5/$30 per 1M tokens vs $0.9/$2.7 per 1M tokens, roughly 5.6× apart on input.
Which has the bigger context window?
Effectively neither — 1M tokens vs 1M tokens 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 Hunyuan Hy4 together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Hunyuan Hy4 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?
Hunyuan Hy4 — released November 4, 2026, about 55 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.