# S2SServiceBench: A Multimodal Benchmark for Last-Mile S2S Climate Services

arXiv: https://arxiv.org/abs/2602.14017 · HTML: https://mlsanity.com/paper/2602.14017/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations](https://mlsanity.com/paper/2506.13651/) (2025)
- [In-the-Flow Agentic System Optimization for Effective Planning and Tool Use](https://mlsanity.com/paper/2510.05592/) (2025)
- [GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks](https://mlsanity.com/paper/2411.19325/) (2024)
- [Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents](https://mlsanity.com/paper/2509.23141/) (2025)
- [ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction](https://mlsanity.com/paper/2402.00712/) (2024)
- [MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark](https://mlsanity.com/paper/2508.07575/) (2025)
- [Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving](https://mlsanity.com/paper/2503.21821/) (2025)
- [WeatherQA: Can Multimodal Language Models Reason about Severe Weather?](https://mlsanity.com/paper/2406.11217/) (2024)
- [CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting](https://mlsanity.com/paper/2409.19058/) (2024)
- [SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading](https://mlsanity.com/paper/2406.10421/) (2024)
- [AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science](https://mlsanity.com/paper/2502.01159/) (2025)
- [MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs](https://mlsanity.com/paper/2510.01691/) (2025)
- [RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts](https://mlsanity.com/paper/2508.12291/) (2025)
- [CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows](https://mlsanity.com/paper/2511.20109/) (2025)
- [SO-Bench: A Structural Output Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2511.21750/) (2025)
- [EWE: An Agentic Framework for Extreme Weather Analysis](https://mlsanity.com/paper/2511.21444/) (2025)
- [QMBench: A Research Level Benchmark for Quantum Materials Research](https://mlsanity.com/paper/2512.19753/) (2025)

## Abstract (arXiv)

Subseasonal-to-seasonal (S2S) forecasts play an essential role in providing a decision-critical weeks-to-months planning window for climate resilience and sustainability, yet a growing bottleneck is the last-mile gap: translating scientific forecasts into trusted, actionable climate services, requiring reliable multimodal understanding and decision-facing reasoning under uncertainty. Meanwhile, multimodal large language models (MLLMs) and corresponding agentic paradigms have made rapid progress in supporting various workflows, but it remains unclear whether they can reliably generate decision-making deliverables from operational service products (e.g., actionable signal comprehension, decision-making handoff, and decision analysis & planning) under uncertainty. We introduce S2SServiceBench, a multimodal benchmark for last-mile S2S climate services curated from an operational climate-service system to evaluate this capability. S2SServiceBenchcovers 10 service products with about 150+ expert-selected cases in total, spanning six application domains - Agriculture, Disasters, Energy, Finance, Health, and Shipping. Each case is instantiated at three service levels, yielding around 500 tasks and 1,000+ evaluation items across climate resilience and sustainability applications. Using S2SServiceBench, we benchmark state-of-the-art MLLMs and agents, and analyze performance across products and service levels, revealing persistent challenges in S2S service plot understanding and reasoning - namely, actionable signal comprehension, operationalizing uncertainty into executable handoffs, and stable, evidence-grounded analysis and planning for dynamic hazards-while offering actionable guidance for building future climate-service agents.