Berk Kalelioğlu
Research interests
Berk focuses on machine learning, agentic AI tools, and large and small language models (LLMs and SLMs).He is part of the AIMultiple benchmark team, conducting assessments and providing insights to help readers understand emerging technologies and their real-world applications.
Professional experience
He began his career as a Tech Project Lead at ODTU IVME-R, where he led a project to build physical quantum and pseudorandom number generators.After his tenure at IVME-R, he co-founded a game development company and released a game on Steam.
He later shifted his career toward AI and joined AIMultiple as a Researcher.
Education
Berk holds a Bachelor’s degree in Mathematics from Ankara University.Latest Articles from Berk
Time Series Classification Benchmark: Foundation Models vs Classical Methods
We benchmarked 13 time series classification methods, from pretrained time series foundation models to a 22-feature baseline from 2019, on 33 UCR/UEA datasets under one frozen protocol. That is 14,638 recorded method-dataset-resample cells, 11,874 of them scored. The chart compares 12 methods on the 15 univariate datasets every one of them completed, each dataset run…
AIM-Decision: Jev vs Clef vs LLMs
Decision models, also called System One models, score a fixed set of options instead of generating text token by token. We tested 59 decision models on 1,655 classification questions, such as rating a security flaw or a product recall, and ran 46 of them on 50 browser tasks. See AIM System One Index for combined…
Always-On Agents: Claude Duet vs Dots vs Grok Bot
Always-on agents keep working after you close the app. Each one runs on a computer that keeps its files and memory, starts tasks on a schedule or when something happens, and messages you when it needs a decision. We compared six of them: OpenAI Dots, Grok Bot, Meta Muse, Claude Duet, Hermes Agent and OpenClaw.…
MCP Gateway Benchmark: Latency & Security of 6 Gateways
An MCP gateway sits between an AI agent and the tools it calls, and vendors position it as the security layer for that traffic. We benchmarked six MCP gateways against one instrumented backend on a single box, measuring added latency, per-tool authorization, content protection, and audit completeness. A product appears against a control only if…
Tabular Models Benchmark: Performance Across 19 Datasets
We benchmarked 13 tabular learning models on 19 real-world datasets with roughly 272,000 samples, ranging from 435 to 48,800 rows. Every model ran with 5-fold cross-validation on identical splits. The results also feed the AIM Tabular Index, which combines them with the public TabArena and BeyondArena leaderboards. Each dataset is a round-robin of head-to-head matches…
AIM Agentic Web Benchmark
Agents rely on web interfaces to complete web tasks. To compare task completion across web interfaces, we built the AIM Agentic Web Benchmark and ran 100 tasks through 8 interfaces, 5 times each, for 4,000 scored results. Bright Data CLI and Bright Data MCP completed 3.6 and 3.8 more tasks per 100 than Zenrows CLI,…
AIM Agentic Marketing Benchmark
We are introducing the AIM Agentic Marketing Benchmark, which measures agent performance on three marketing workflows: competitive gap analysis, ABM target list preparation, and a personalized sales deck. We also ran a separate website reputation audit in which agents examined AIMultiple’s English-language content and reported verifiable issues with factual accuracy, citations, consistency, freshness, functionality, grammar,…
A-CODE-CLI Bench: Agentic CLI Benchmark
Agentic CLI tools are AI coding tools that can create and delete files, run commands, plan, and execute the coding of the entire project. We benchmarked the leading tools across 10 real-world web development scenarios, performing ~600 atomic validation checks per agent and more than ~5,000 total automated test executions, including backend logic, frontend functionality,…
Agentic IT: Can AI Agents Design a Benchmark
We tested 16 models on a benchmark design in text-to-SQL and tool calling. Each model built one benchmark per topic, for a total of 32 submissions. No submission passed every rubric criterion. The agents could build and run tests, but none demonstrated both a blank-answer test and a correct-answer test of their own scorer. Text-to-SQL…
AIM Enterprise: Agentic Enterprise Benchmark
Enterprises use LLMs every day for their regular tasks. To find the most cost-efficient LLMs, we designed AIM Enterprise, an agentic enterprise benchmark, where we used 69 real enterprise tasks across strategy, marketing, HR, sales, and operations. Two judge models scored every file that passed the checks. On 32.7% of the individual scores the two…
AIMultiple Newsletter
1 free email per week with the latest B2B tech news & expert insights to accelerate your enterprise.