AI Paper Atlas

Research map / Large language models / Agents, code and math

ChemEval: A Multi-level and Fine-grained Chemical Capability Evaluation for Large Language Models

Yuqing Huang, Rongyang Zhang, Xuesong He, Xuyang Zhi, Hao Wang, Nuo Chen, Zongbo Liu, Xin Li, Feiyang Xu, Deguang Liu, Huadong Liang, YiLi and 7 more

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery

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 changedWhereMeasuredEffect
add 3-shot examples to the prompt (ablation)OpenAI-o1 · ReactTRF1: 25.00 -> 60.00Improved
add 3-shot examples to the prompt (ablation)GPT-4o · ReactTRF1: 32.00 -> 71.00Improved
add 3-shot examples to the prompt (ablation)DeepSeek-V3 · SubEAccuracy: 61.26 -> 75.78Improved
add 3-shot examples to the prompt (ablation)Llama3.3-8B · SATaskLLM Score: 38.40 -> 29.00Hurt
add 3-shot examples to the prompt (ablation)ChemDFM · TempEF1: 74.33 -> 41.00Hurt
add 3-shot examples to the prompt (ablation)ChemSpark · LRecF1: 37.60 -> 16.80Hurt
scale Qwen2.5 from 7B to 72B (ablation)Qwen2.5 · MCTaskAccuracy: 59.60 -> 67.20Improved
scale Qwen2.5 from 7B to 72B (ablation)Qwen2.5 · CalcTaskLLM Score: 43.60 -> 61.90Improved
scale Qwen2.5 from 7B to 72B (ablation)Qwen2.5 · MolPCAccuracy: 64.04 -> 48.13Hurt
scale Qwen2.5 from 7B to 72B (ablation)Qwen2.5 · CatRecF1: 0.00 -> 0.00No clear effect
use thinking model OpenAI-o1 instead of GPT-4oGPT-4o · MCTaskAccuracy: 66.80 -> 74.00Improved
use thinking model DeepSeek-R1 instead of DeepSeek-V3DeepSeek-V3 · MCTaskAccuracy: 76.00 -> 82.40Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy