Fugu Ultra v2.0 vs Kimi K3.1 Pro
Sakana AI · Global | Moonshot AI · 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 Kimi K3.1 Pro for sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base or terminal-bench 4.0 of 65.7% (moonshot) and 67% as measured by artificial analysis. On a tight budget at scale, Kimi K3.1 Pro is the value pick.
Fugu Ultra v2.0 (Sakana AI) and Kimi K3.1 Pro (Moonshot AI) 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. Kimi K3.1 Pro is moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: Kimi K3.1 Pro 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: 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: Kimi K3.1 Pro is the newer model by about 43 days (released October 23, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Fugu Ultra v2.0 | Kimi K3.1 Pro |
|---|---|---|
| Provider | Sakana AI (Global) | Moonshot AI (China) |
| Released | September 10, 2026 | October 23, 2026 |
| Context window | 1M tokens (~1,500 pages) | 1M tokens (~1,573 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, 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
Kimi K3.1 Pro is comparatively weak here — most benchmarks are internal or use differing harnesses; no SWE-bench Verified figure published
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; Kimi K3.1 Pro does not.
1M-token context window
Fugu Ultra v2.0
Kimi K3.1 Pro is comparatively weak here — very high output-token use: roughly 150M output tokens across the Artificial Analysis index
Sparse MoE with 2.8T total and about 104B active parameters, post-trained from the Kimi K3 base
Kimi K3.1 Pro
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
Terminal-Bench 4.0 of 65.7% (Moonshot) and 67% as measured by Artificial Analysis
Kimi K3.1 Pro
Moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4 — and it runs cheaper at $2/$10 per 1M tokens.
Artificial Analysis Intelligence Index of 55, second only to Claude Opus 5.5 (58) among the models AI Weekly lists
Kimi K3.1 Pro
Moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4 — and it is the newer of the two.
Lowest cost at scale
Kimi K3.1 Pro
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
→ Kimi K3.1 Pro
At $2/$10 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
→ Kimi K3.1 Pro
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 sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base
→ Kimi K3.1 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.
Kimi K3.1 Pro: where it fits
Moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4. Released October 23, 2026 by Moonshot AI, it is built for sparse MoE with 2.8T total and about 104B active parameters, post-trained from the Kimi K3 base, terminal-Bench 4.0 of 65.7% (Moonshot) and 67% as measured by Artificial Analysis, artificial Analysis Intelligence Index of 55, second only to Claude Opus 5.5 (58) among the models AI Weekly lists, and standard API price cut by a third versus K3 to $2/$10 per million tokens (Highspeed tier $4/$20).
Its trade-offs: weights promised by November 4, 2026 and not confirmed public as of November 3; license terms not yet disclosed, very high output-token use: roughly 150M output tokens across the Artificial Analysis index, self-hosting is impractical - about 1.4 TB of raw weights even at 4-bit, and most benchmarks are internal or use differing harnesses; no SWE-bench Verified figure published. 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 Kimi K3.1 Pro overlap enough that the right pick depends on your specific job. Kimi K3.1 Pro costs less per token; Kimi K3.1 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, Kimi K3.1 Pro for sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both Fugu Ultra v2.0 and Kimi K3.1 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 pricingFrequently asked questions
Is Fugu Ultra v2.0 or Kimi K3.1 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 Kimi K3.1 Pro leans toward sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Fugu Ultra v2.0 or Kimi K3.1 Pro?
Kimi K3.1 Pro 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?
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 Kimi K3.1 Pro together?
Yes — a multi-model platform like LumiChats gives you Fugu Ultra v2.0, Kimi K3.1 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 Kimi K3.1 Pro?
Kimi K3.1 Pro — released October 23, 2026, about 43 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.