pith. sign in
Pith Number

pith:PQRUAG7C

pith:2025:PQRUAG7C2OCFREFZNGQJWSKI5I
not attested not anchored not stored refs resolved

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Bruce Leon, Can Zhang, Chao Liu, Chenxuan Xie, Dading Chong, Jian Chen, Jing Ren, Meng Cao, Peilin Zhou, Qichen Ye, Sixin Hong, Xiang Ying, Yifan Shao, Yining Hua, Yuxin Gu, Zhiling Jin

A new benchmark shows most LLMs score below 20% when browsing the Chinese web for verifiable facts.

arxiv:2504.19314 v2 · 2025-04-27 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{PQRUAG7C2OCFREFZNGQJWSKI5I}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Despite their strong conversational and retrieval capabilities, most models struggle severely: a large number achieve accuracy rates below 10%, and only a handful exceed 20%. Even the best-performing system, OpenAI's DeepResearch, reaches just 42.9%.

C2weakest assumption

The two-stage quality control protocol produces questions that are genuinely high-difficulty and have unique verifiable answers without hidden shortcuts or English leakage.

C3one line summary

BrowseComp-ZH is a new benchmark of 289 Chinese web questions where even the strongest LLM agents reach only 42.9% accuracy.

References

22 extracted · 22 resolved · 9 Pith anchors

[1] From Local to Global: A Graph RAG Approach to Query-Focused Summarization 2024 · arXiv:2404.16130
[2] arXiv preprint arXiv:2407.12468 (2024) 2024
[3] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 2025 · arXiv:2501.12948
[4] arXiv preprint arXiv:2411.19478 (2024) 2024
[5] arXiv preprint arXiv:2502.15690 (2024) 2024

Formal links

2 machine-checked theorem links

Cited by

21 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:12.902539Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

7c23401be2d3845890b969a09b4948ea380c39eb900fe2bc41f90797b1ade5f8

Aliases

arxiv: 2504.19314 · arxiv_version: 2504.19314v2 · doi: 10.48550/arxiv.2504.19314 · pith_short_12: PQRUAG7C2OCF · pith_short_16: PQRUAG7C2OCFREFZ · pith_short_8: PQRUAG7C
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/PQRUAG7C2OCFREFZNGQJWSKI5I \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 7c23401be2d3845890b969a09b4948ea380c39eb900fe2bc41f90797b1ade5f8
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "78aa5bd77c508b2215bb6b4bdc00d4604a190ccd376fce9ce842115b491fc286",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-04-27T17:32:43Z",
    "title_canon_sha256": "95280f255ef9a9626cd5d169bfca73a75d904d8baf0ab8b2a6939d97de709b07"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2504.19314",
    "kind": "arxiv",
    "version": 2
  }
}