DeepCoder

DeepCoder

Agentica Project
Fugu-Ultra v1.1

Fugu-Ultra v1.1

Sakana AI
+
+

Related Products

  • Robin by Atera
    532 Ratings
    Visit Website
  • PackageX OCR Scanning
    48 Ratings
    Visit Website
  • JetBrains Junie
    12 Ratings
    Visit Website
  • Eurekos
    93 Ratings
    Visit Website
  • Aikido Security
    239 Ratings
    Visit Website
  • Setplex
    10 Ratings
    Visit Website
  • Criminal IP ASM
    21 Ratings
    Visit Website
  • Mitti (by SafetyCulture)
    647 Ratings
    Visit Website
  • QBench
    152 Ratings
    Visit Website
  • Evertune
    1 Rating
    Visit Website

About

DeepCoder is a fully open source code-reasoning and generation model released by Agentica Project in collaboration with Together AI. It is fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning, achieving a 60.6% accuracy on LiveCodeBench (representing an 8% improvement over the base), a performance level that matches that of proprietary models such as o3-mini (2025-01-031 Low) and o1 while using only 14 billion parameters. It was trained over 2.5 weeks on 32 H100 GPUs with a curated dataset of roughly 24,000 coding problems drawn from verified sources (including TACO-Verified, PrimeIntellect SYNTHETIC-1, and LiveCodeBench submissions), each problem requiring a verifiable solution and at least five unit tests to ensure reliability for RL training. To handle long-range context, DeepCoder employs techniques such as iterative context lengthening and overlong filtering.

About

Fugu-Ultra v1.1 is Sakana AI’s upgraded multi-agent orchestration model for complex coding, agentic work, and advanced reasoning. Rather than relying on one model, it dynamically coordinates a diverse pool of frontier models, selecting and combining specialized agents for each task while presenting the system through a single model interface. The v1.1 orchestration upgrade incorporates newer frontier models and improves performance across every tracked benchmark, with gains of up to 7.9 points over v1.0 and particularly strong results on ProgramBench and Terminal Bench 2.1. Fugu can now be used directly inside Claude Code through Claude Code-compatible endpoints, bringing a coordinated team of models into familiar terminal workflows for writing, debugging, reviewing, and executing code. A one-command installer configures the integration on Ubuntu and macOS, while manual setup is available for Windows and other environments.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Developers, researchers, and enthusiasts wanting a tool to generate, debug, or reason about code without relying on proprietary models

Audience

Developers seeking to use multiple coordinated frontier AI models directly within Claude Code for coding, debugging, reasoning, and execution tasks

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version
Free Trial

Pricing

$6 per 1M tokens (input)
$6 per 1M tokens (input), $36 per 1M tokens (output)
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 5.0 / 5
ease 5.0 / 5
features 5.0 / 5

Pros & Cons from Real Users

Pros

  • Fugu-Ultra v1.1 is really interesting from a developer’s point of view because it feels like a different approach from the usual “one giant model does everything” setup. Instead, it acts more like an intelligent orchestration layer that can route work across multiple frontier models and agent patterns. That makes a lot of sense for coding and agentic workflows. Real development tasks are messy, and different parts of the job need different strengths: planning, repo search, debugging, terminal work, reasoning, code generation, and cleanup. I also like that Sakana added a Claude Code-compatible interface. Being able to use Fugu directly inside developer workflows makes it feel much more practical than something you only test in a browser or benchmark page. The benchmark gains are impressive too. If the reported improvements on coding and terminal tasks hold up in real projects, Fugu-Ultra v1.1 could be a strong option for developers building serious coding agents.

Cons

  • The main downside is that orchestration adds complexity. When a system is coordinating multiple models behind the scenes, I want strong transparency, logging, debugging tools, and predictable behavior before I trust it deeply in production. I would also want to test latency and cost carefully. Multi-agent systems can be powerful, but they can also become expensive or slow if they overthink simple tasks.

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Agentica Project
Founded: 2025
United States
agentica-project.com

Company Information

Sakana AI
Founded: 2023
Japan
sakana.ai/fugu-1-1-claude-code-interface/

Alternatives

DeepSWE

DeepSWE

Agentica Project

Alternatives

Claude Opus 5

Claude Opus 5

Anthropic
Devstral 2

Devstral 2

Mistral AI
Claude Fable 5

Claude Fable 5

Anthropic
Devstral Small 2

Devstral Small 2

Mistral AI
Claude Mythos 5

Claude Mythos 5

Anthropic
DeepScaleR

DeepScaleR

Agentica Project
Sakana Fugu

Sakana Fugu

Sakana AI

Categories

Categories

Integrations

Hugging Face
Sakana Fugu
Sakana Fugu Ultra
Together AI

Integrations

Hugging Face
Sakana Fugu
Sakana Fugu Ultra
Together AI
Claim DeepCoder and update features and information
Claim DeepCoder and update features and information
Claim Fugu-Ultra v1.1 and update features and information
Claim Fugu-Ultra v1.1 and update features and information