做环境数据分析或地理空间智能体的开发者，这个基准能帮你快速验证模型在真实 API 调用场景下的能力，DeepSeek V3.2 的性价比值得一试。
GeoNatureAgent Benchmark 是首个针对环境分析智能体的基准测试，要求智能体通过结构化工具调用真实地理空间 API 完成任务。该基准包含 93 个任务，覆盖 18 个类别，如市政分析、多轮对话、空间推理、错误处理等，基于西班牙和葡萄牙的三个环境指标和 16 个工具进行评估。测试了 7 个 LLM（Claude Sonnet 4、DeepSeek V3.2 等），Claude Sonnet 4 以 60.8% 准确率领先，DeepSeek V3.2 以 56.3% 紧随其后，且成本仅为 Claude 的 1/11。比较类任务（如接近值比较）所有模型均为 0%，暴露了系统推理局限。该基准比通用 GIS 基准更具区分度，准确率低 25-35 个百分点。基准、测试工具和 API 均已开源。
GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models
Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs. We introduce the GeoNatureAgent Benchmark, the first benchmark for environmental analysis agents that operate via structured tool calls to a production-style geospatial API. It comprises 93 tasks across 18 categories, covering municipality analysis, multi-turn conversation, spatial reasoning, cross-indicator synthesis, error handling and recovery, ranking, comparison, multilingual understanding, habitat analysis, and task rejection. Tasks are evaluated against an open, self-hostable API serving three environmental indicators across Spain and Portugal via sixteen tools. We evaluate seven LLMs (Claude Sonnet 4, DeepSeek V3.2, GLM-5, Gemini 2.5 Pro, Qwen3-235B, GPT-OSS-120B, Llama 4 Scout) under three temperature-1.0 seeds, reporting capability and per-case cost as orthogonal axes. We find: (1) Claude Sonnet 4 leads at 60.8% +/- 0.8%, followed by DeepSeek V3.2 at 56.3% +/- 3.1%, with no other model above 51%; (2) the cost-accuracy Pareto frontier is occupied mostly by open-weight models, with DeepSeek V3.2 offering 93% of Claude's capability at 11x lower cost ($0.011/case); (3) comparison tasks remain universally unsolved (0% on close-value comparisons), exposing systematic reasoning limits; and (4) structured tool calling against a real API is more discriminative than general-purpose GIS benchmarks, with accuracies 25-35 points lower. We further show extensibility by integrating BigEarthNet V2 land cover for Portugal alongside Spanish CO2 and erosion indicators. The benchmark, harness, and self-hostable API are publicly available.