By Vilius Vystartas | May 2026 Ten more models through the same 10 agent coding tasks. Two tied the...
By Vilius Vystartas | May 2026
Ten more models through the same 10 agent coding tasks. Two tied the all-time record. One cost $0.0002. The other hit the score at $0.0018 — cheaper than most models scoring 70%.
Batch 10 was the cheapest one yet.
The Leaders
Two models scored 90% with zero hard fails, joining MiniMax M2 Her and Baidu Ernie 4.5 300B as the highest-scoring models on this benchmark:
This Half-Gigabyte AI Model Runs Local Agents on Your Phone - Decrypt
Alibaba's proprietary Qwen3.7-Max can run for 35 hours autonomously and supports external harnesses like Anthropic's Claude Code
半价享顶级性能！天工 SkyClaw Agent 模型限时免费试用-36氪
Alibaba's latest AI model ran autonomously for 35 hours to optimize code for its own custom chip
Alibaba unveils Qwen3.7-Max, its flagship AI model for real-world tasks
By Vilius Vystartas | May 2026 I tested another 10 models across the same 10 agent coding tasks....
The past week pushed three quiet shifts into the open. A coding model matched the frontier at a tenth...
The Problem: AI Agents Are Expensive By Default If you're using AI agents like Manus AI,...
OpenBMB's 1B-parameter model MiniCMP 5 brings MCP support and agentic tool use to on-device AI—but it has trouble with logic…
Every time a coding agent underperforms, the default move is to swap in a bigger model. I wanted to...
I’ve been building backend systems for over a decade. I’ve seen AI code generators go from “cute...
