@heyshrutimishra: 35B nearly matching 1T on agent benchmarks changes the cost math entirely. Apodex 1.1 mini scores 27.7 on APEX-Agents. …
Summary
Apodex 1.1 mini achieves competitive performance on agent benchmarks with significantly fewer parameters than larger models like Kimi K2.6, highlighting deployment cost advantages.
View Cached Full Text
Cached at: 08/25/26, 02:11 PM
35B nearly matching 1T on agent benchmarks changes the cost math entirely.
Apodex 1.1 mini scores 27.7 on APEX-Agents.
Kimi K2.6 hits 27.9 using ~1 trillion parameters, roughly 30x more compute.
Deployment cost is the moat.
Apodex (@Apodex_AI): Meet Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Open Source Harness: https://t.co/hXoOuuWhlk Open Weights: https://t.co/tudzx5etWt
We’re excited to introduce Apodex 1.1, our new model family built to scale agentic intelligence for professional work.
🧠
Similar Articles
@heyshrutimishra: Apodex 1.0 dropped and the architecture is genuinely different. It's post-trained on Qwen3.5 as a self-evolving system:…
Apodex 1.0 is a self-evolving AI system post-trained on Qwen3.5, achieving SOTA on BrowseComp, DeepSearchQA, and HLE-text. Its 4B mini model outperforms 30B-class models, with an AgentOS runtime for task orchestration. Open weights available.
Releasing Apodex-1.0 Smol Models (0.8B, 2B, 4B Open-Weights) optimized for Agentic Verification + AgentHarness Evals
Apodex releases open-weight small models (0.8B, 2B, 4B) specialized for agentic verification tasks, along with the AgentHarness evaluation framework for local agent workflows.
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Apodex 1.1 improves sustained, verifiable progress on complex real-world tasks by scaling executable environments and training agents for long-horizon coordination, achieving leading performance with a smaller 35B-parameter model.
A 35B model beat a 120B one on my coding agent, 95% vs 53%. Build your own benchmark.
A developer built a custom benchmark for coding AI agents and found that a 35B-parameter model outperformed a 120B-parameter one when the harness was optimized, highlighting the importance of tailored evaluation over generic specifications.
Kimi K2.6 vs Minimax M3: 5x the cost for worse results? I ran the tests.
A hands-on comparison of Kimi K2.6 and Minimax M3 in real agent workflows shows M3 costs roughly 5x less while delivering nearly identical quality, making it more cost-effective for production systems.