Research map / Large language models / Agents, code and math
EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language Models
Wanghan Xu, Xiangyu Zhao, Yuhao Zhou, Xiaoyu Yue, Ben Fei, Fenghua Ling, Wenlong Zhang, LEI BAI
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| provide 3 initial CoT steps as hints at inference (ablation) | DeepSeek-V3 · Earth-Silver FIB | FIB accuracy (%): 12.80 -> 45.60 | Improved |
| provide 3 initial CoT steps as hints at inference (ablation) | GPT-4o · Earth-Silver FIB | FIB accuracy (%): 18.40 -> 55.60 | Improved |
| provide 1 initial CoT step (ablation) | DeepSeek-V3 · Earth-Silver FIB | FIB accuracy (%): 12.80 -> 21.60 | Improved |
| provide 2 initial CoT steps (ablation) | GPT-4o · Earth-Silver FIB | FIB accuracy (%): 18.40 -> 38.80 | Improved |
| move from Earth-Iron to harder Earth-Silver | mean of 11 LLMs · Multiple choice | accuracy (%): 89.53 -> 54.40 | Hurt |
| move from Earth-Iron to Earth-Silver | mean of 11 LLMs · Free response | win rate (%): 72.86 -> 41.15 | Hurt |
| scale Llama-3.1 from 8B to 70B | Llama-3.1 · Earth-Iron MC | accuracy (%): 59.41 -> 91.56 | Improved |
| scale Llama-3.1 from 8B to 70B | Llama-3.1 · Earth-Gold | SES: 0.3301 -> 0.2453 | Hurt |
Closest papers by meaning
- AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science (NeurIPS 2025 · similarity 0.88)
- Assessing Large Language Models on Climate Information (ICML 2024 · similarity 0.87)
- SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research (AAAI 2024 · similarity 0.86)
- MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models (AAAI 2026 · similarity 0.86)
- GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing (CVPR 2026 · similarity 0.86)
- Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
