Authors
Our writers
-
Senior model reviewer · 1 piece on file
Karl Strauchman
Karl Strauchman leads model reviews for AI Model Report. He has spent years working with long-context evaluation harnesses and is responsible for the desk’s scoring methodology on instruction-following and long-document recall. His pieces cover the full reviewer arc: capability claim, replication attempt, verdict.
-
Benchmarks desk · 1 piece on file
Linnea Halberg
Linnea runs the benchmarks desk. She maintains the desk’s private regression suites for reasoning, math, and tool use, and writes the methodology notes that accompany every numbered comparison the site publishes. She is the desk’s voice on leaderboard inflation and contamination risk.
-
Open source & model weights · 0 pieces on file
Lars Iverson
Lars Iverson covers the open-weights ecosystem. He reads architecture diffs for a living and tracks every notable checkpoint release from Meta, Mistral, Qwen, DeepSeek, and the long tail. His beat is licences, parameter counts, and what the weights actually let an operator do.
-
Multimodal beat · 1 piece on file
Lucia Castellan
Lucia Castellan covers vision, audio, and the messy edges where modalities meet. She maintains the desk’s chart-and-document benchmarks and has been running every new vision model against them for years. Her reviews always include at least one image and one document the model failed on.
-
Coding models specialist · 1 piece on file
Adebayo Olufemi
Adebayo Olufemi reviews coding models for AI Model Report. He maintains a 2,000-task evaluation suite spanning eleven languages and writes the desk’s annual coding-model survey. Years on the coding-models beat have left him allergic to demoware that does not pass a real test runner.
-
Inference & serving · 1 piece on file
Aiko Tanaka
Aiko covers the serving stack — vLLM, SGLang, TensorRT-LLM, and the kernels underneath. Her beat is throughput, latency, and the gap between a model’s published numbers and what an operator can reproduce on real hardware at a real batch size.