CoBuddy vs Perceptron Mk1 vs Sakana Namazu
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Baidu
CoBuddy
48/100- ECI—
- Price$0.28 / $1.13
- Context131K
Perceptron
Perceptron Mk1
47/100- ECI—
- Price$0.15 / $1.50
- Context33K
Sakana AI
Sakana Namazu
51/100- ECI—
- Price$0.95 / $4.00
- Context262K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 51/100, CoBuddy 48/100, Perceptron Mk1 47/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest pricePerceptron Mk1Perceptron Mk1 $0.487 · CoBuddy $0.492 · Sakana Namazu $1.71 per 1M tokens (3:1 blend)
- Longest contextSakana NamazuSakana Namazu 262,144 · CoBuddy 131,072 · Perceptron Mk1 32,768 tokens
- Widest inputsPerceptron Mk1 and Sakana NamazuCoBuddy: Text · Perceptron Mk1: Text, Images, Video · Sakana Namazu: Text, Images, PDFs
- Self-hostingNo confirmed open weightsAll three are available only through APIs
| Measure | Weight | CoBuddy | Perceptron Mk1 | Sakana Namazu |
|---|---|---|---|---|
| Price | 50% | 62 | 62 | 37 |
| Inputs & features | 30% | 35 | 45 | 80 |
| Context window | 20% | 32 | 11 | 43 |
| Specs & price only | 100% | 48/100 | 47/100 | 51/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Perceptron Mk1Perceptron | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.28 | $0.15 (best) | $0.95 |
| Output | $1.13 (best) | $1.50 | $4.00 |
| Cached input | — | — | $0.15 |
| Blended (3:1) | $0.492 | $0.487 (best) | $1.71 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 3 providers | Official Sakana AI API |
| Limits | |||
| Context window | 131,072 tokens | 32,768 tokens | 262,144 tokens (best) |
| Max output | 65,536 tokens (best) | 8,192 tokens | 65,536 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | — | — | sakana-namazu |
| API providers | 1 | 3 | 7 (best) |
| Released | May 6, 2026 | May 12, 2026 | Aug 3, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
CoBuddy$5.06
- Perceptron Mk1$4.50
Sakana Namazu$17.50
Which should you choose?
Which is better: CoBuddy, Perceptron Mk1 or Sakana Namazu?
There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 51/100, CoBuddy 48/100, Perceptron Mk1 47/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, CoBuddy, Perceptron Mk1 or Sakana Namazu?
Perceptron Mk1 is cheaper at $0.15 input / $1.50 output per million tokens (median across 3 API providers). CoBuddy costs $0.28 input / $1.13 output per million tokens (median across 1 API provider); Sakana Namazu costs $0.95 input / $4.00 output per million tokens (official Sakana AI API price). At a typical mix of three input tokens to one output token, that is $0.487 per million tokens for Perceptron Mk1 versus $0.492 for CoBuddy (1× as much) and $1.71 for Sakana Namazu (3.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. CoBuddy has not been scored yet, Perceptron Mk1 has not been scored yet and Sakana Namazu has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for CoBuddy, Perceptron Mk1 and Sakana Namazu yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Perceptron Mk1 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Sakana Namazu has the largest context window at 262,144 tokens, against 131,072 for CoBuddy and 32,768 for Perceptron Mk1. Maximum output per response: CoBuddy up to 65,536, Perceptron Mk1 up to 8,192, Sakana Namazu up to 65,536 tokens.
Which can read images, PDFs, audio or video?
CoBuddy accepts text; Perceptron Mk1 accepts text, images and video; Sakana Namazu accepts text, images and PDFs. Perceptron Mk1 handles the widest range of inputs.
Are any of these open source?
No. CoBuddy, Perceptron Mk1 and Sakana Namazu are proprietary and only available through APIs and apps.
Which is newer?
Sakana Namazu is the newest, released Aug 3, 2026. Perceptron Mk1 came out May 12, 2026; CoBuddy came out May 6, 2026.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.