They summarize our coverage. We write it.
Newsletters like this one rebroadcast our headlines - often without the full review, the source reading, or the analysis underneath. Our weekly briefing sends the work they paraphrase, straight from the desk, before they get to it.
Free, weekly, no spam. One email every Tuesday. Unsubscribe anytime.
AI Benchmarks & Tools Analyst
James is a software engineer turned tech writer who spent six years building backend systems at a fintech startup in Chicago before pivoting to full-time analysis of AI tools and infrastructure. His engineering background means he doesn't just read the spec sheet - he runs the benchmarks, profiles the latency, and checks whether the marketing claims hold up under real workloads.
He studied Computer Science at the University of Illinois at Urbana-Champaign, where he first got hooked on natural language processing during a senior research project on sentiment analysis. He later completed a certificate in data journalism from Northwestern's Medill School.
At Awesome Agents, James owns the leaderboards and tool comparison coverage. He maintains the site's benchmark tracking methodology and is the person who actually runs the numbers before publishing any ranking. He is also an open-source advocate and contributes to several projects in the LLM inference space.
Based in Chicago, IL.
A detailed comparison of Moonshot AI's 1T-parameter Kimi K2.5 against Microsoft's 14B Phi-4 - the most extreme size gap in frontier AI, with 71x the parameters but vastly different use cases.
Comparing Kimi K2.5 and Qwen3.5 Flash - Moonshot AI's trillion-parameter frontier model against Alibaba's cheapest and fastest API offering.
Comparing Kimi K2.5's 1T-parameter benchmark dominance against Qwen3.5-122B-A10B's extraordinary parameter efficiency - and why the smaller model is harder to dismiss than the numbers suggest.
Comparing Kimi K2.5's trillion-parameter benchmark dominance against Qwen3.5-27B's single-GPU accessibility - two models from entirely different tiers that both have compelling use cases.
A detailed comparison of Kimi K2.5 and Qwen3.5-35B-A3B - a 1T parameter frontier model with agent swarms versus a 35B model that runs on a single consumer GPU.
DeepSeek V3.2 is a 671B-parameter MoE model activating 37B per token that delivers frontier-class reasoning and coding at the lowest API price in the industry - $0.14/$0.28 input, $0.42 output per million tokens.
Google's cheapest Gemini model pairs a 1M-token context window with $0.10/$0.40 per million token pricing, multimodal input, and 359 tokens/second throughput for high-volume production workloads.
Zhipu's GLM-4.7-Flash is a 30B-A3B MoE model that posts 59.2% on SWE-bench Verified and 79.5% on tau2-Bench while running on a single RTX 4090 - MIT licensed and free via the Z.AI API.
Google Gemma 3 27B is a 27B dense multimodal model supporting text and vision with a 128K context window, 140+ languages, and single-GPU deployment - the most capable open model at its size class.
OpenAI's budget API workhorse pairs 128K context with $0.15/$0.60 per million token pricing, solid coding benchmarks, and the broadest third-party ecosystem of any small model.
Meta's Llama 4 Maverick packs 400B total parameters into a 128-expert MoE architecture with only 17B active per token, beating GPT-4o on Chatbot Arena while matching DeepSeek V3 on reasoning at half the active parameters.
Meta's Llama 4 Scout is a 109B-total, 17B-active MoE model with 16 experts and a 10M-token context window - the longest of any open-weight model - with native multimodal support for text and images.
