Coding benchmark
PaperBench leaderboard
Every model the catalog carries a published PaperBench value for, ranked by that value.
CategoryCoding
MeasureLong-horizon agent evaluation
TasksAI research-paper reproduction
DifficultyFrontier autonomous research and engineering
Published byQwen3.8-Max: A New Bar for Coding and Cowork
A research-reproduction benchmark that asks agents to recreate the contributions of AI papers from the paper alone.
PaperBench ranking
1 model with a published PaperBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Long-horizon agent evaluation |
|---|---|---|---|
| 1 |  Qwen3.8 Max | Alibaba | 93.0 |
Evidence key: Observed
Rows are ordered by the value Qwen3.8-Max: A New Bar for Coding and Cowork published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.