# AI4AI-Bench leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-ai4ai-bench

AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement. Every model the catalog carries a published AI4AI-Bench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Four-hour code rewrite followed by sealed training and held-out evaluation |
| Tasks | 10 AI training-algorithm design tasks |
| Difficulty | End-to-end AI research and algorithm design |
| Published by | [AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement](https://arxiv.org/abs/2608.20318) |

Tests whether coding agents can improve the training algorithm inside an existing AI research codebase, then survive a sealed training run and held-out evaluation.

## AI4AI-Bench ranking

No model in the catalog has a published AI4AI-Bench score. The benchmark is defined by AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
