PaperBench

PaperBench: Evaluating AI's Ability to Replicate AI Research

Agents must replicate 20 ICML 2024 Spotlight and Oral papers from scratch: understand the paper, write a codebase and run the experiments, in a container with GPU access. Grading uses author-co-developed hierarchical rubrics (8,316 gradable leaf nodes) applied by an LLM judge, giving a replication score from 0 to 100. The Code-Dev variant grades code only. It measures long-horizon research engineering, with a measured human (ML PhD) baseline for comparison.

43.4%
IterativeAgent o1-high
official
2025-04-02 → 2025-04-02: 21% → 43.4%
Released
2025-04
Maintainer
OpenAI (Starace et al.)
Status
active
Contamination
medium
Metric
replication score (percent, ↑)
Tasks
20
Domains
research ml-engineering code tool-use
human
no measured baseline

Notes. The paper reports that top ML PhDs outperformed models on a 3-paper subset over 48 hours, but the figure is on a subset and not comparable to the full 20-paper score, so no human_baseline is recorded. The repository leaderboard has not been updated since the April 2025 launch; papers and rubrics are public.

Full ledger

SystemDeveloperScoreDateSourceConditions
IterativeAgent o1-highOpenAI43.4%officialsplit: code-dev scaffold: IterativeAgent reasoning_effort: high
PaperBench Code-Dev leaderboard, 3 runs, +/-0.8.
IterativeAgent o1-high (36h limit)OpenAI26%officialsplit: full scaffold: IterativeAgent reasoning_effort: high
Top of the repository leaderboard; 3 runs, +/-0.3, 36-hour limit.
IterativeAgent o1-high (24h limit)OpenAI24.4%officialsplit: full scaffold: IterativeAgent reasoning_effort: high
Repository leaderboard, 3 runs, +/-0.7, 24-hour limit.
BasicAgent claude-3.5-sonnetAnthropic21%officialsplit: full scaffold: BasicAgent
Repository leaderboard, 3 runs, +/-0.8.