AI Paper Atlas

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

AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

Changzhi Zhou, Ao Liu, Yuchi Deng, Zhiying Zeng, Tao Zhang, Haotian Zhu, Jianwei Cai, Yue Mao, Chenchen Zhang, Lingyun Tan, ZiyanXU, Bohui Zhai and 4 more

ICLR 2026 · Large language models › Agents, code and math · approach: Code generation benchmarks · 26 citations (OpenAlex)

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
use reasoning mode instead of non-reasoning mode (ablation)Claude Opus 4 · AutoCodeBenchPass@1 average (%): 50.9 -> 52.4Improved
use reasoning mode instead of non-reasoning mode (ablation)Qwen3-32B · AutoCodeBenchPass@1 average (%): 31.0 -> 41.7Improved
add up to three turns of sandbox execution-error feedback refinement (ablation)DeepSeek-V3-0324 · AutoCodeBenchPass@1 average (%): 48.1 -> 59.7Improved
add up to three turns of sandbox execution-error feedback refinement (ablation)Qwen2.5-Coder-32B-Instruct · AutoCodeBenchPass@1 average (%): 35.8 -> 47.4Improved
add sandbox feedback refinement (ablation)Qwen3-8B · AutoCodeBenchPass@1 average (%): 23.3 -> 30.2Improved
filter out easy problems using DeepSeek-Coder-V2-Lite (10 samples) (ablation)AutoCodeGen data pool · AutoCodeBench subset (6 languages)Pass@1 average (%): Gemini2.5 Pro 51.4 -> 31.6; Qwen2.5-Coder-32B-Instruct 39.9 -> 17.1Improved
add LLM-as-Critic filtering after difficulty filtering (ablation)AutoCodeGen data pool · AutoCodeBench subset (6 languages)Pass@1 average (%): Gemini2.5 Pro 31.6 -> 38.7; DeepSeek-V3-0324 25.7 -> 31.6Improved
evaluate on multi-logical problems instead of full dataset (ablation)all evaluated models · AutoCodeBench (multi-logic subset, 1,622 problems)Pass@1Hurt
evaluate on low-resource languages versus popular languages (ablation)top models · AutoCodeBenchPass@1 spread across model families: popular 50.4-53.8; low-resource 45.3-62.0Mixed
scale up model size within Qwen3 thinking series (ablation)Qwen3 (Think) series · AutoCodeBenchPass@1 average (%): Qwen3-1.7B 11.2 -> Qwen3-8B 28.5 -> Qwen3-32B 41.7Improved

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