SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.06480 · NAACL · 2024

Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks

Dahua Lin, Kai Chen, Haodong Duan, Songyang Zhang, Chonghua Wang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.06480.json · badge: /api/ran/2404.06480.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
open-compass/ada-leval canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
GPT_context_window Ran
ran, honoured the contract we drafted
open-compass/ada-leval/ada_leval/api.py
pointer only (licence: NONE) · get_code("a868f0afe2141be4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, open-compass/ada-leval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cn_string Ran
ran, violated the contract we drafted
open-compass/ada-leval/ada_leval/smp.py
pointer only (licence: NONE); the stored copy get_code serves, from Slimshilin/Position-Bias-Analyzer-Demo, is pointer only (licence: NONE) · get_code("e8277b4e02292cbe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, open-compass/ada-leval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

d2df Ran
ran; our contract draft was wrong, not the code
open-compass/ada-leval/ada_leval/smp.py
pointer only (licence: NONE) · get_code("a94c49bf751fef5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, open-compass/ada-leval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_logger Ran
ran; our contract draft was wrong, not the code
open-compass/ada-leval/ada_leval/util.py
pointer only (licence: NONE) · get_code("a50476e2d7c30009")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, open-compass/ada-leval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

timestr Ran
ran; our contract draft was wrong, not the code
open-compass/ada-leval/ada_leval/smp.py
pointer only (licence: NONE) · get_code("27bd620b8b50c5ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, open-compass/ada-leval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
cn_string 3 other papers
1 dated earlier, 2 later
2403.08604 (2024-03)
Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study
2406.07791 (2024-06)
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
ijcai2025_0762 (2025 (year only))
M 4 Bench: A Benchmark of Multi-domain Multi-granularity Multi-image Understanding for Multi-modal Large Language Models
get_logger 1 other paper
1 dated earlier
2403.04732 (2024-03)
How Far Are We from Intelligent Visual Deductive Reasoning?

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, the large language model (LLM) community has shown increasing interest in enhancing LLMs' capability to handle extremely long documents. As various long-text techniques and model architectures emerge, the precise and detailed evaluation of models' longtext capabilities has become increasingly important. Existing long-text evaluation benchmarks, such as L-Eval and LongBench, construct long-text test sets based on open-source datasets, focusing mainly on QA and summarization tasks. These datasets include test samples of varying lengths (from 2k to 32k+) entangled together, making it challenging to assess model capabilities across different length ranges. Moreover, they do not cover the ultralong settings (100k+ tokens) that the latest LLMs claim to achieve. In this paper, we introduce Ada-LEval, a length-adaptable benchmark for evaluating the long-context understanding of LLMs. Ada-LEval includes two challenging subsets, TSort and BestAnswer, which enable a more reliable evaluation of LLMs' long context capabilities. These benchmarks support intricate manipulation of the length of test cases, and can easily produce text samples up to 128k tokens. We evaluate 4 state-ofthe-art closed-source API models and 6 opensource models with Ada-LEval. The evaluation results demonstrate the limitations of current LLMs, especially in ultra-long-context settings. Our code is available at https://github. com/open-compass/Ada-LEval.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.06480")
get_code_for_paper("2404.06480")
have("2404.06480")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.06480.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.06480.svg)](https://syntology.ai/paper/2404.06480)

Connect an agent — have() is free.