# MARCA: A Checklist-Based Benchmark for Multilingual Web Search

arXiv: https://arxiv.org/abs/2604.14448 · HTML: https://mlsanity.com/paper/2604.14448/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge](https://mlsanity.com/paper/2411.19799/) (2024)
- [All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages](https://mlsanity.com/paper/2411.16508/) (2024)
- [MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents](https://mlsanity.com/paper/2508.13186/) (2025)
- [LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild](https://mlsanity.com/paper/2510.14240/) (2025)
- [Search Arena: Analyzing Search-Augmented LLMs](https://mlsanity.com/paper/2506.05334/) (2025)
- [WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks](https://mlsanity.com/paper/2506.01952/) (2025)
- [BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams](https://mlsanity.com/paper/2307.05410/) (2023)
- [Automatic Legal Writing Evaluation of LLMs](https://mlsanity.com/paper/2504.21202/) (2025)
- [TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time](https://mlsanity.com/paper/2501.07482/) (2025)
- [Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams](https://mlsanity.com/paper/2311.14169/) (2023)
- [Sabi'a-4 Technical Report](https://mlsanity.com/paper/2603.10213/) (2026)
- [Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation](https://mlsanity.com/paper/2509.14477/) (2025)
- [PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese](https://mlsanity.com/paper/2511.17808/) (2025)
- [BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning](https://mlsanity.com/paper/2508.21294/) (2025)
- [LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated News](https://mlsanity.com/paper/2602.13543/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as sources of information, yet their reliability depends on the ability to search the web, select relevant evidence, and synthesize complete answers. While recent benchmarks evaluate web-browsing and agentic tool use, multilingual settings, and Portuguese in particular, remain underexplored. We present textscMARCA, a bilingual (English and Portuguese) benchmark for evaluating LLMs on web-based information seeking. textscMARCA consists of 52 manually authored multi-entity questions, paired with manually validated checklist-style rubrics that explicitly measure answer completeness and correctness. We evaluate 14 models under two interaction settings: a Basic framework with direct web search and scraping, and an Orchestrator framework that enables task decomposition via delegated subagents. To capture stochasticity, each question is executed multiple times and performance is reported with run-level uncertainty. Across models, we observe large performance differences, find that orchestration often improves coverage, and identify substantial variability in how models transfer from English to Portuguese. The benchmark is available at https://github.com/maritaca-ai/MARCA